tag:blogger.com,1999:blog-33381745272620618482024-03-07T19:31:33.640-08:00Coyle's InFormationComments on the digital age, which, as we all know, is 42.Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.comBlogger371125tag:blogger.com,1999:blog-3338174527262061848.post-32279261266515470882023-10-13T09:04:00.004-07:002023-10-13T09:18:41.706-07:00Words<p></p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhaK5MBie4XGD8yt-JRxSjuFRZn2_ZcRvJoYH1M3XhwxzpWLCMa3z0282bD7g_gT4lmOf9KZpKjnVxP1S_2P2XaTujYGrr6CtxQuDnGUiRC93HoWLpVX4JIjLUpUA0As1K9ktYCZjS08yoiZYXX6DRpELkYnwRR1TFyyAH2W8kPpUwZXNcYbhQpwLW6UUFX/s1360/zipf.jpg" imageanchor="1" style="clear: right; float: right; margin-bottom: 1em; margin-left: 1em;"><img border="0" data-original-height="1360" data-original-width="946" height="320" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhaK5MBie4XGD8yt-JRxSjuFRZn2_ZcRvJoYH1M3XhwxzpWLCMa3z0282bD7g_gT4lmOf9KZpKjnVxP1S_2P2XaTujYGrr6CtxQuDnGUiRC93HoWLpVX4JIjLUpUA0As1K9ktYCZjS08yoiZYXX6DRpELkYnwRR1TFyyAH2W8kPpUwZXNcYbhQpwLW6UUFX/s320/zipf.jpg" width="223" /></a></div><br />In 1949, George Kingsley Zipf published the book "Human Behavior and the Principle of Least Effort" in which he develops what became known as "<a href="https://en.wikipedia.org/wiki/Zipf%27s_law">Zipf's law</a>." <br /><p></p>
<p>Zipf was one of the
first to do research in word frequency. A linguist by profession, for some
reason he decided to study statistical patterns of word frequency in texts. He ended up
developing a law based on efficiency and effort that proved to be true across an
astonishingly wide range of writings both in English and in other languages, and was even extended beyond language to other human activities.[*] </p>
<p>His law essentially says (if I may reduce it down to an essence) that for reasons of efficiency, some words are used often, in different combinations and with different meanings, while more specialized words become the long tail of speech and writing. Much of "Human Behavior" consists of detailed formulas and charts based on the few full texts that he had to work with. All show that the
same statistical curve was obtained with some words being very high frequency
and the curve dropping off rapidly until the proverbial long tail was arrived
at. The figures themselves could be seen as an interesting glitch in linguistic
reality but what made Zipf’s law powerful was his explanation of the reason for
the consistency of the data.</p><p>Zipf explained his theory using a workbench as a metaphor. In a well-organized workbench, the tools that were kept closest to the worker would be those with the widest uses, the proverbial hammer that can be used for a great number of chores. In that close circle would be tools that could also be combined to tackle tasks that neither could complete alone. As you would move further out from the center, you would find tools that were used less often but that become increasingly specialized in their functions. Presumably you would eventually arrive at a tool that could do only one job, a tool that you almost never needed. <br /></p>
<p>His pioneering work made use, of all things, of a concordance of James Joyce's Ulysses, a text that contains many words that are not in my toolbox. Joyce was notably fanciful in his use of language, and yet the statistical measure that Zipf obtained from Ulysses was comparable to measures obtained from other texts, including some in the Chinese language.</p><p>Zipf showed, to my mind, that the more frequent a word is the less it tells you about its meaning in the text in which it is found. A brick doesn't tell you what the house looks like. <br /></p>
<p>Later research into term frequency failed to understand what Zipf was saying and took
a high term frequency to indicate that the word in question was of importance
related to the number of appearances in a text. This is clearly not what he
said and a quick way to realize that is to realize that the first text that he
ran his theory on was James Joyce’s Ulysses - a text that defies prediction. (The current AI "predictive" language can produce the upper echelons of Zipf's frequency curve, but not the beauty of the Joycean long tail.)<br /></p>
<p>It seems obvious that an individual string of characters unbroken by whitespace is not necessarily a unit of meaning. Think about the meanings of "ice" and "cream" and how these differ from the meaning of "ice cream". This is more of a problem in some languages that others. Some languages, like Italian, have a single word ("gelato") for that concept; others, like German, have a way of avoiding the whitespace split ("<span class="HwtZe" lang="de"><span class="jCAhz ChMk0b"><span class="ryNqvb">Eiscreme") by putting the elements of "eis" (ice) and "creme" (cream) together into a single word. (I am beginning to think that the German language method of creating composite words that create a single unit for a concept is superior to the English use of using separate words for composite concepts.)</span></span></span></p><p>The problem that I see is that while you can observe human activity,
including writing, and turn that observation into numbers, it's rarely
clear what the numbers represent besides, well, being numbers. This is
even true in the area of linguistics that was Zipf's main bailiwick. We
are so accustomed to the definition of "word" as any characters
bookended with some whitespace character that we fail to think about the
great complexity that language presents and that the use of whitespace
in writing has its purposes but does not define meaning.</p><p>----- <br /></p><p>[*] Zipf's law has been used to
describe the relative sizes of cities in a country [1], in genetics [2],
company income distribution [3], and more. </p><p>[1] Xavier Gabaix, Zipf's Law for Cities: An Explanation, <i>The Quarterly Journal of Economics</i>, Volume 114, Issue 3, August 1999, Pages 739–767, <a data-google-interstitial="false" href="https://doi.org/10.1162/003355399556133">https://doi.org/10.1162/003355399556133</a></p><p>[2]Furusawa, Chikara, and Kunihiko Kaneko. "Zipf’s law in gene expression." <i>Physical review letters</i> 90, no. 8 (2003): 088102.</p><div class="gs_citr" tabindex="0">[3] <br /><div class="gs_citr" tabindex="0">Okuyama, K., Takayasu, M. and Takayasu, H., 1999. Zipf's law in income distribution of companies. <i>Physica A: Statistical Mechanics and its Applications</i>, <i>269</i>(1), pp.125-131.</div> </div><p> </p>Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com0tag:blogger.com,1999:blog-3338174527262061848.post-39254908429565485552023-06-14T08:15:00.002-07:002023-06-14T08:15:53.916-07:00The Real Bard, Tis a Pity<p> There are many things that bother me about the recently released chatbots, one of which is their a-historical nature. This lack of attention to any time other than today is a fault in much of technology thinking, but in the chatbots it is not difficult to demonstrate. And such a demonstration came about in an email exchange on a list of folks who are usually quite critical of technology developments as they affect society.</p><p>I expressed my concern:</p><p></p><blockquote>I'm particularly bothered by the proposal that there is one giant
language that is the sum of a mass of written expressions. First,
written language and spoken language have differences. Second, there
are language subsets, like medicine or law or any other specialty,
and you can't just mix those in with a huge database of web
documents; you can't mix blog posts and post-modern academic
writing as if they were the same language. Topicality is important,
as is context.
<br />
<br />The other thing that bothers me, and has bothered me with other tech
developments, is that the approach is a-historical, as if today is
the only time that has ever existed. Language notoriously changes
over time. Can chatGPT do Shakespeare? Bronte? Dante? Is it ok to
lose those because they aren't "now"?
</blockquote><p>Someone then ran the query "Please write the story of Little Red Riding Hood
using Shakespearean English" with the bots ChatGPT and Bard. Here are excerpts from the responses:</p><p><span class="" style="color: #343541;"><span class="" style="caret-color: rgb(52, 53, 65); white-space: pre-wrap;"><b class=""></b></span></span></p><p></p><blockquote><p></p><p><span class="" style="color: #343541;"><span class="" style="caret-color: rgb(52, 53, 65); white-space: pre-wrap;"><b class="">ChatGPT: </b></span></span><span class="" style="caret-color: rgb(55, 65, 81); color: #374151; white-space: pre-wrap;">Once upon a time, in a land far from mine own,</span></p><p></p><p class="" style="--tw-border-spacing-x: 0; --tw-border-spacing-y: 0; --tw-ring-color: rgba(69,89,164,0.5); --tw-ring-offset-color: #fff; --tw-ring-offset-shadow: 0 0 transparent; --tw-ring-offset-width: 0px; --tw-ring-shadow: 0 0 transparent; --tw-rotate: 0; --tw-scale-x: 1; --tw-scale-y: 1; --tw-scroll-snap-strictness: proximity; --tw-shadow-colored: 0 0 transparent; --tw-shadow: 0 0 transparent; --tw-skew-x: 0; --tw-skew-y: 0; --tw-translate-x: 0; --tw-translate-y: 0; border: 0px solid rgb(217, 217, 227); box-sizing: border-box; caret-color: rgb(55, 65, 81); color: #374151; margin: 0px 0px 1.25em; white-space: pre-wrap;">There lived a maiden fair, of beauty and grace,
She was called Little Red Riding Hood, yon tale to unfold,
Whose journey through the woods led her to a dire chase.</p><p class="" style="--tw-border-spacing-x: 0; --tw-border-spacing-y: 0; --tw-ring-color: rgba(69,89,164,0.5); --tw-ring-offset-color: #fff; --tw-ring-offset-shadow: 0 0 transparent; --tw-ring-offset-width: 0px; --tw-ring-shadow: 0 0 transparent; --tw-rotate: 0; --tw-scale-x: 1; --tw-scale-y: 1; --tw-scroll-snap-strictness: proximity; --tw-shadow-colored: 0 0 transparent; --tw-shadow: 0 0 transparent; --tw-skew-x: 0; --tw-skew-y: 0; --tw-translate-x: 0; --tw-translate-y: 0; border: 0px solid rgb(217, 217, 227); box-sizing: border-box; caret-color: rgb(55, 65, 81); color: #374151; margin: 1.25em 0px; white-space: pre-wrap;">Her mother beseeched her, with love and concern,
"Take this basket, dear child, and tread with care,
For the woods be fraught with danger untold,
Beware the wolf that lurks in shadows there."</p><p class="" style="--tw-border-spacing-x: 0; --tw-border-spacing-y: 0; --tw-ring-color: rgba(69,89,164,0.5); --tw-ring-offset-color: #fff; --tw-ring-offset-shadow: 0 0 transparent; --tw-ring-offset-width: 0px; --tw-ring-shadow: 0 0 transparent; --tw-rotate: 0; --tw-scale-x: 1; --tw-scale-y: 1; --tw-scroll-snap-strictness: proximity; --tw-shadow-colored: 0 0 transparent; --tw-shadow: 0 0 transparent; --tw-skew-x: 0; --tw-skew-y: 0; --tw-translate-x: 0; --tw-translate-y: 0; border: 0px solid rgb(217, 217, 227); box-sizing: border-box; caret-color: rgb(55, 65, 81); color: #374151; margin: 1.25em 0px; white-space: pre-wrap;">Little Red Riding Hood, in her scarlet cloak,
Embarked on her path, with naught but innocence,
Through verdant glades and whispering leaves,
She ventured forth, sans any recompense.</p></blockquote><p><span class="" style="color: #343541;"><span class="" style="caret-color: rgb(52, 53, 65); white-space: pre-wrap;"><b class=""></b></span></span></p><blockquote><span class="" style="color: #343541;"><span class="" style="caret-color: rgb(52, 53, 65); white-space: pre-wrap;"><b class="">BARD: </b></span></span><span class="" style="background-color: #f8fafd; caret-color: rgb(68, 71, 70); color: #444746; white-space: pre;"><b class="">I</b>n a village, there dwelt a maid,
With a cloak of red so bright,
She was known by all as Little Red Riding Hood.
One day, her mother bade her go
To her grandmother's house,
With a basket of food to cheer her up.
Along the way, Little Red Riding Hood met
A big, bad wolf,
Who asked her where she was going.
"To my grandmother's house," she said,
"To take her some food."</span></blockquote><span class="" style="background-color: #f8fafd; caret-color: rgb(68, 71, 70); color: #444746; white-space: pre;"></span> These look rather impressive, coming from a bot. They are written as poetry, sometimes rhyming, although in some cases the rhymed words are nonsense (see "recompense" in the ChatGPT version). There is some attempt to use Elizabethan language, throwing in a "dwelt" and a "doth". But nothing about this gets even close to the poetry and language of Shakespeare. I don't have a true Shakespearean version of Little Red Riding Hood, but here is some actual Shakespeare:<p></p><p></p><blockquote>In his bright radiance and collateral light
<br />Must I be comforted, not in his sphere.
<br />Th’ ambition in my love thus plagues itself:
<br />The hind that would be mated by the lion
<br />Must die for love. ’Twas pretty, though a plague,
<br />To see him every hour, to sit and draw
<br />His archèd brows, his hawking eye, his curls
<br />In our heart’s table—heart too capable
<br />Of every line and trick of his sweet favor.
<br />But now he’s gone, and my idolatrous fancy
<br />Must sanctify his relics. Who comes here?
</blockquote><br />
<br />and
<br />
<br /><blockquote>There was a time when all the body’s members
<br />Rebelled against the belly, thus accused it:
<br />That only like a gulf it did remain
<br />I’ th’ midst o’ th’ body, idle and unactive,
<br />Still cupboarding the viand, never bearing
<br />Like labor with the rest, where th’ other instruments
<br />Did see and hear, devise, instruct, walk, feel,
<br />And, mutually participate, did minister
<br />Unto the appetite and affection common
<br />Of the whole body. The belly answered </blockquote>The bots return a weak sauce, using a few old-sounding words in a mostly modern text. The results are more modern Red Riding Hood than Shakespeare. Red Riding Hood has its <a href="https://en.wikipedia.org/wiki/Little_Red_Riding_Hood#History">own history</a>, some of which actually pre-dates the Bard of Avon. The algorithmic prediction applied here seems to be based on a database that readily mixes modern language and that of the 16th century, languages that should be seen as distinct. The one thing the bots seem to have "learned" is that Shakespeare means "written like poetry," which ChatGPT used to create rhyming text and Bard simply used to make short line lengths, usually at logical points in the sentence.<p></p><p>Language is and has been ever-changing for all of the years of human existence. It simply cannot be taken out of context. John McWhorter, in his <i>The Power of Babel</i>*, gives examples of how language changes with "He blew up the post office" of 1830 and "He made love to me" of 1935. Those are both from recent years compared to the 1600 of Shakespeare, yet they did not mean then what they mean today.** We can be dismissive of "wrong" use of words in teenage slang, but that slang is language with a context. It is a fast-changing language, but an easily observable example of the fact that language is in constant change.<br /></p><p>That change has a history, and its future is not predictable. Bots can calculate the next likely word based on a very large database, but we should turn to teenagers for the future of language, and to past writers <i>in their context</i> to learn where we've been.<br /></p><span><a name='more'></a></span><p>* McWhorter John. <i>The Power of Babel a Natural History of Language</i>. Perennial 2001.</p><p>** "Blew up" in 1830 means that you gave them a piece of your mind; "made love to" in 1935 meant to woo or court. <br /></p><p><br /></p><p class="" style="--tw-border-spacing-x: 0; --tw-border-spacing-y: 0; --tw-ring-color: rgba(69,89,164,0.5); --tw-ring-offset-color: #fff; --tw-ring-offset-shadow: 0 0 transparent; --tw-ring-offset-width: 0px; --tw-ring-shadow: 0 0 transparent; --tw-rotate: 0; --tw-scale-x: 1; --tw-scale-y: 1; --tw-scroll-snap-strictness: proximity; --tw-shadow-colored: 0 0 transparent; --tw-shadow: 0 0 transparent; --tw-skew-x: 0; --tw-skew-y: 0; --tw-translate-x: 0; --tw-translate-y: 0; border: 0px solid rgb(217, 217, 227); box-sizing: border-box; caret-color: rgb(55, 65, 81); color: #374151; margin: 1.25em 0px; white-space: pre-wrap;"></p><p></p><p> </p><p> </p><p></p>Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com0tag:blogger.com,1999:blog-3338174527262061848.post-6722785460347007692023-04-13T10:29:00.000-07:002023-04-13T10:29:24.493-07:00What is Controlled Digital Lending? The Origin Story<p> The bulk of the reporting on the <a href="https://www.courtlistener.com/docket/17211300/hachette-book-group-inc-v-internet-archive/?order_by=desc">lawsuit</a> between publishers (four of them, led by Hachette) and the Internet Archive's version of Controlled Digital Lending hits one of these points of view:<br /></p><ul style="text-align: left;"><li> The publishers are evil, money-grubbing idiots going after the generous, saintly Internet Archive</li><li> The Internet Archive is evil, stealing from the poor publishers and even poorer writers</li></ul><p>As is so often the case, it really is more compex than that. I will try to throw a bit of clarity into mix here, mainly by talking about some of the realities of library service in the 21st century, and the origins of controlled digital lending.<br /></p><h3 style="text-align: left;">The Origins of CDL</h3><p>Michelle M. Wu, a law librarian and law professor, wrote a piece for the Law Library Journal in 2011 explaining the dilemmas faced by law libraries and proposing a modest solution.</p><p></p><blockquote>"Building a Collaborative Digital Collection: A Necessary Evolution in Libraries" LAW LIBRARY JOURNAL Vol. 103:4 [2011-34]) (<a href="https://papers.ssrn.com/sol3/papers.cfm?abstract_id=1832826">online</a>)</blockquote><p></p><p>The solution is what became Controlled Digital Lending. The reasons she lays out are the key.<br /><br />The main argument that Wu puts forth (and that I find convincing) is this: library users either want or actually need to be able to access materials remotely, which means in electronic formats over a network. Increasingly, materials that libraries wish to provide are available from publishers in those electronic formats. The catch, however, is that libraries are not able to <i>own</i> materials in electronic formats, but instead can only subscribe to access services. It is this lack of ownership that is the rub. If a library loses its digital subscription for some reason, such as no longer being able to afford it, it not only loses access to future materials, it loses access to all of the past materials that were included in that subscription. This puts libraries in the terrible position of having to decide between fulfilling their role as the reliable repository and archive of material in their subject area, or of serving the needs of library users. As Wu points out, libraries are already struggling to afford the materials that they feel they should be collecting, so purchasing these materials both in hard copy for archival purposes and also in digital form for user service is entirely beyond the pale.<br /><br />What Wu suggests in her article is a variation on Inter-Library Loan, combined with a library collective purchasing plan. A cooperative group of law libraries would combine purchasing physical resources for those items that are rarely used but that should be available to the researchers who need them. This is not a revolutionary idea - library consortia have been making use of this kind of approach for a significant amount of time. The difference in Wu's plan is that as items are requested from the consortial holdings, they will be digitized and the digital format will be the one loaned. To stay within the intention of copyright law, in particular First Sale, Wu offers that the digital file will be loaned as a surrogate for the physical copy:<br /></p><blockquote>"Materials acquired would be digitized, and only the number of copies acquired in print for each subsequently digitized document would circulate at any given time. The print copy would be stored for archival purposes; only the digital copy would “circulate.”" Wu p.535</blockquote>The physical resource would fulfill the need for an archival copy, and the digital resource would allow lending to any networked member of the cooperative group. Her solution assumes an effective digital rights management system that would make the loan a loan and not a pirate-able copy. <br /><br />Wu carefully covers all of the potential legal objections, and points out the various areas of US copyright law that might be touched on with her proposal. Specific areas are<a href="https://www.law.cornell.edu/uscode/text/17/109"> First Sale</a>, <a href="https://www.law.cornell.edu/uscode/text/17/107">Fair Use</a>, and the various <a href="https://www.law.cornell.edu/uscode/text/17/108">exceptions</a> to the copyright law that are applied to libraries. She defends the digitization as format-shifting, not unlike the format-shifting that is done for sound recordings as the technology for that medium has changed. <br /><blockquote>"It is the work itself that is copyrighted, not the form." Wu p. 541</blockquote>She also addresses what would be an obvious objection of rights holders, that the digital copy is substituting for a purchase. The hard copy would be purchased by the consortium, and given her statement that these would primarily be low-use materials that many libraries would not themselves purchase, no harm would be done to the market which would be limited.<br /><br />The argument that I find strongest is that of preservation: the US copyright law does allow libraries to make copies of works for the purposes of preservation if no equivalent copy is available for purchase. (Section 108 subsection c) Using the argument that the purpose of the library is to preserve as well as to make works available, Wu says:<br /><blockquote>"In cases where a digital version is available only for license, a library could argue that such a license is not equivalent to either the print copy or a digital copy they would make, because both of these items would be owned by the library and the licensed digital version would not." Wu p. 539</blockquote><h3 style="text-align: left;">Context Counts</h3>Controlled Digital Lending is the technology: the digitization of paper works and the lending of the digital copy using management software that prevents piracy of the digital file. It is the context that makes Wu's proposal different to the implementation of controlled digital lending at the Internet Archive.<br /><ul style="text-align: left;"><li>Wu's proposal was for a consortium of law libraries serving their own users; the IA's implementation was open to anyone on the web</li><li>Wu's proposal was for academic materials of low use; the IA's included popular works</li><li>The works in Wu's proposal would have been selected with specific research purposes in mind; the IA's collection was an opportunistic group of books that they had often obtained as second-hand - therefore no research purpose could be argued. (Purpose is one of the Fair Use factors.)</li><li>Wu's proposal argued for the need of libraries to preserve materials that otherwise would not be preserved; the Archive is indeed an archive, known for its preservation of web sites that otherwise would be lost. However, the popular books named in the lawsuit against the Archive are already "preserved" in thousands of libraries who have those physical books on their shelves - the preservation argument is not easily supplied. </li></ul><p><a href="https://www.hathitrust.org/">HathiTrust</a>, which is a consortium of libraries that originally contributed to the Google Books project, is an example that follows Wu's approach. HathiTrust stores digitized copies of books and follows the ruling related to Google Books that searching of in-copyright works is permitted, but not reading. HathiTrust developed its own controlled digital lending service as an <a href="https://www.hathitrust.org/ETAS-Description">emergency service</a> for when a member library is temporarily closed due to a disaster. In that case, users from the member library can borrow digitized books held by the member library in hard copy. <br /></p><p>Wu even suggests that libraries might share the burden of digitization by providing digitized copies to libraries that own the books in hard copy. This latter, though, was one of the things that got the Internet Archive in trouble because it became a "digital lending broker" for other libraries, adding their hard copy count to the Archive's lending "units" including some of books owned by the publishers in the lawsuit.<br /></p><h3 style="text-align: left;">The Upshot</h3>The argument presented by Wu is quite strong and is justified through her careful reading of copyright law, in particular as that law applies to libraries. The extension of her proposal to popular reading materials and to an unlimited user base changes everything. Libraries do have specific collections, identified users, and stated purposes that guide their acquisitions. Something I feel strongly about - that is absent from so many modern information activities - is that effective information use requires purposeful resource selection and organization. Any mass of stored resources is only as valuable as its organization and coherence. In some cases, a "less" that is well organized can be more informative than a "more" that may lack the key works in a subject area. It may be old-fashioned on my part, but I adhere to the concept of defined user goals and the deliberate collection of specific works in support of user learning. This is what I read in Wu's work but which I do not see in the Archive's activities. <br /><br />I think Wu's context could be understood as falling within the confines of copyright law. I'm not sure that the Archive's case does. I do hope that this current lawsuit does not result in a rejection of digitization for lending for all libraries.<br /><br /><p></p>Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com0tag:blogger.com,1999:blog-3338174527262061848.post-7235340384502266022023-04-07T12:09:00.148-07:002023-04-09T09:33:33.774-07:00Libraries, the law, and equality<p><i> </i></p><div class="separator" style="clear: both; text-align: center;"><i><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi_mjx-BhfRQfY8DW6mGa7TxfeKR9csbqBbyBWGLPr3B3jGozAgfcZJALIGUu_arYYvQLynYZpEnbcf1Evb7Dui6hECiT9kKvxuY5lC2AhVcJQMpCbnmD8-5AGZfrHIEIuYr7L2Sm5-e6USTM1jNtrrfGIsOSDZgX5lslITqGArtqyUZv9UpkMV2nRhtg/s323/equal.jpg" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="156" data-original-width="323" height="155" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi_mjx-BhfRQfY8DW6mGa7TxfeKR9csbqBbyBWGLPr3B3jGozAgfcZJALIGUu_arYYvQLynYZpEnbcf1Evb7Dui6hECiT9kKvxuY5lC2AhVcJQMpCbnmD8-5AGZfrHIEIuYr7L2Sm5-e6USTM1jNtrrfGIsOSDZgX5lslITqGArtqyUZv9UpkMV2nRhtg/s320/equal.jpg" width="320" /></a></i></div><i><br /></i><p></p><p style="margin-left: 40px; text-align: left;"></p><blockquote><i>In the spirit of "everyone is equal under the law", it is equally illegal for both a starving man and a billionaire to steal a loaf of bread. Or to copy a book.<br /></i></blockquote><p></p><h3 style="text-align: left;"><i> </i>Libraries for the People</h3><p>It was not all that long ago when "library" often referred to the room in a rich man's home where he stored books that were only available to him, and perhaps members of his family (especially if they were not female). Other libraries, usually larger ones, were attached to prestigious educational institutions and accessible by people worthy of that prestige (which would not include non-white nor female people). We are fortunate today that we have these things called "public libraries," libraries that serve everyone regardless of their wealth, their race, or their gender. <br /><br />Here's the catch: public libraries are generally small and modestly funded by the local community. A moderately sized public library has 50,000 - 100,000 volumes. A large public library may have up to 500,00 volumes. A large university library has many more. Harvard University library claims to have 20 million book volumes, 400 million manuscripts, and 10 million photographs. Stanford University library may have at least 12 million book volumes. Michigan State University libraries have about 7 million book volumes. The British Museum Library lays claim to 170 and 200 million items of which 13.5 million are printed books and e-books. There is no question that the members of our community who are served solely by public libraries, while they have unprecedented access to books, are not able to study the full range of printed knowledge of our world. To whit, the university libraries are often referred to as "research libraries" while the local public libraries are called "reading libraries." This separates us into "readers" and "researchers," and while you might conclude that any literate person can read, only those associated with large libraries will be able to avail themselves of the tools to do research.</p><h3 style="text-align: left;">Digital Access</h3><p>Much of the research done in academe consumes and creates journal articles. Originally issued only in paper, and mailed to libraries and departments, journal articles have been available in digital form from the mid-1990's and today it would be unusual for an article-based publication to be issued only in paper. Journal owners have digitized the full run of publications, as have cooperative projects based in academia. A researcher or student at a Western university is likely to have more than a century of scientific, technical or social science academic article output available through the Internet, any day, any time, and perhaps from any place. Anyone from less wealthy nations will have less access, although perhaps just a tad more than they had when the articles were issued only in paper.</p><p></p><p>The story is different with books. While most academic articles have been converted to digital form, the same cannot be said of books. It is only recently that publishers have issued their books in electronic form using the electronic files that are now part and parcel of the publishing process. That only takes care of current publications, however. Sitting in libraries are centuries of one-off publications in book form. Books from this vast backlog must be
digitized from the existing physical copy. Projects by libraries and educational institutions to digitize the monographic backlog, similar to those that succeeded in digitizing the journal output of the ages, have not been accomplished. There are various reasons why that is the
case: the sheer number of book pages that would need to be digitized is
huge; non-destructive digitization of bound volumes is difficult and often does not yield good results; partnering with publishers for this task is hampered by the fact that numerous books from the 20th century and older are
"orphaned," meaning that although they may be under copyright their
copyright holder cannot be found; and compared to modern ebooks,
digitized books have little to recommend them for reading, although
with their searchable text they may be useful for research. <br /></p><p>The only efforts to digitize the backlog of books, Google Book Search and the digitizing by the Internet Archive, have resulted in lawsuits against those organizations. The suit against Google concluded that digitization is allowed as long as the digitized books are provided for purposes of searching but not reading. The Internet Archive took the view that books are for reading, an approach that I find hard to oppose.</p><p></p><h3 style="text-align: left;">Reading vs Research</h3><p>Reading and research are related but different activities. Reading is often associated with books, and includes books on scientific and academic topics as well as fiction, from great literature to beach reads. While few non-researchers read academic articles, some members of academe do read books as part of their research. Of course, many people also read for pleasure; reading is a key means of acquiring culture, along side other activities like taking in performances of various arts.<br /><br />If you are not at one of those institutions with a large research library, the only way you may have to see the content of many books is by accessing a digitized book. A digitized book is not the same reading experience as the ebook produced by publishers. A digitized book has not been produced from an electronic file of its contents as an ebook has been. Instead, each page of the physical book has been photographed, and those images have been analyzed using optical character recognition (OCR) software. The result of the OCR is a text file, and that file will be more or less "lossy" depending on things like the condition of the original book pages, the clarity of the font, the language of the text. </p><p></p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj9CMXgcj4aDiBYjQ_3Ar5_JtOqSgUfJBHw5n13aF9Avmq4L_9bmL5IaFeNpi8o_sMLXcTLV26_MYDe7jywOMNMDtE_W4Bk5mRfPd85EUgktcrK_YvcOj-o32BBcDSdrQpdy9U2Tt9X4RplUHQubmI8onTIEWvnicF2L6U1VV9N7Sd0AIXvhvMCwghd-g/s1114/Screenshot%202023-04-09%20at%209.31.56%20AM.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="248" data-original-width="1114" height="71" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj9CMXgcj4aDiBYjQ_3Ar5_JtOqSgUfJBHw5n13aF9Avmq4L_9bmL5IaFeNpi8o_sMLXcTLV26_MYDe7jywOMNMDtE_W4Bk5mRfPd85EUgktcrK_YvcOj-o32BBcDSdrQpdy9U2Tt9X4RplUHQubmI8onTIEWvnicF2L6U1VV9N7Sd0AIXvhvMCwghd-g/s320/Screenshot%202023-04-09%20at%209.31.56%20AM.png" width="320" /></a></div><p></p><p>Unlike an ebook, reading the digitized book usually means viewing pictures of the books' pages. <br /></p><p> </p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEimQGwMawz9_SGksf2FwxtXsnBWnNI4Cv2-AHjSdEzii7q4CiXK7gC0kOwQhEvl5-ON2hr44e4bB-ukMQstfkiaLP96tiJcL7xdDLkIxuUESHaiD9h7GcMO2iroX3DGOv3XK83U_9VoFTELEQcoDpIMFanzV8YOarbL---v6o0zGVdeav4WmBcKHle9sQ/s1114/Screenshot%202023-04-09%20at%209.04.41%20AM.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="978" data-original-width="1114" height="281" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEimQGwMawz9_SGksf2FwxtXsnBWnNI4Cv2-AHjSdEzii7q4CiXK7gC0kOwQhEvl5-ON2hr44e4bB-ukMQstfkiaLP96tiJcL7xdDLkIxuUESHaiD9h7GcMO2iroX3DGOv3XK83U_9VoFTELEQcoDpIMFanzV8YOarbL---v6o0zGVdeav4WmBcKHle9sQ/s320/Screenshot%202023-04-09%20at%209.04.41%20AM.png" width="320" /></a></div><br /><p></p><p>It's not a great reading experience, but imagine that the book is important for your studies or your work; it would be worth the effort.</p><p>On the other hand, if you are wanting some modern leisure reading and you are in North America, you will be much better served by checking out the book and ebook offerings of your public library. If you are not in North America, and if your locality has a limited public library or no public library at all, then the extra effort that you may need to make to read a digitized book may be worth it to you. If, however, you had the funds to purchase the materials you needed or were associated with an institution that made those materials available to you, it is unlikely that you would choose the less sophisticated and less available copy provided at the Archive.</p><p></p><h3 style="text-align: left;">Hachette, et al., v Internet Archive</h3><p>The above sets out some of the social parameters that we should consider when thinking about the <a href="https://storage.courtlistener.com/recap/gov.uscourts.nysd.537900/gov.uscourts.nysd.537900.188.0.pdf">recent lawsuit</a> relating to Controlled Digital Lending. (See <a href="https://kcoyle.blogspot.com/2023/04/judges-decision-on-internet-archives.html">previous post</a>.) In brief, the Internet Archive has digitized many books and makes them available globally, lending one "copy" at a time. A group of publishers has sued the Archive based on a set of books for which the publishers hold the copyright. The issue is often presented as a test of the concept of Controlled Digital Lending, although only some books are in question in the lawsuit. Those books represent only a portion of the books available at the Archive or in libraries in general. Although one may think of a binary division of books into "still in copyright" and "no longer in copyright" the actual situation is more complex. <br /></p><ol style="text-align: left;"><li>There are the books that are out of copyright, which generally means books from 1924 and earlier in the US. These are not under discussion. However, there is no way to separate the basic copyrighted content of a book, like Mark Twain's Huck Finn from later reprintings that often add some bit of a preface so that the publisher can put a copyright notice on it and pretend to have the rights. Such "books" may be considered in copyright even though the primary content of those books is not. There is unfortunately no penalty for a publisher in slapping a copyright statement onto a book that is not under copyright, as can be seen in my favorite example of a blank journal sold with a copyright notice.</li><li>There are the orphaned works, for which there is no one to assert rights. Either the rights holder (the publisher) no longer exists, or the documentation that would make it possible to assert rights does not exist. Because this is a category of unknowns, it is quite difficult to determine which books are in this category.<br /></li><li>There are works that are not orphaned but the publisher is not asserting rights in relation to Controlled Digital Lending. This may be the majority of the books being loaned by the Archive because there are only four publishers in the lawsuit. We don't know what the other publishers think about the lending.<br /></li><li>There are the books by the four publishers that are included in the lawsuit. These four publishers are asserting that the Archive violated their rights and potentially deprived them of income.</li></ol><p>It would be great to know the figures that would allow us to compare 1-3 with 4. It would also be great to know how many loans were actually made by the Archive of those books in the 4th category. Presumably that figure will inform the penalty that is imposed on the Archive. </p><p>The Archive's defense seems to be solid as it shows that in both the
presence and the absence of its contested service no change was noted
for publisher sales. It is chilling that the judge so readily dismissed the Archive's arguments, and especially chilling if you consider, as a hypothetical, applying this same argument to libraries in general.<br /></p><blockquote>"IA’s experts observed that print sales of the Works in Suit and general demand for library ebooks did not decrease while the Works in Suit were available on IA’s Website; that Amazon rankings for the Works in Suit improved when IA’s digital lending skyrocketed (and government lockdowns were in full effect) at the beginning of the Covid-19 pandemic; and that, despite the removal of the Works in Suit from IA’s library in June 2020, OverDrive checkouts of the Works in Suit did not increase." (Case 1:20-cv-04160-JGK-OTW Document 188 Filed 03/24/23 Page 42)</blockquote><p>That sounds like a good defense, yet the judge dismisses it. <br /></p><blockquote>"But these metrics do not begin to meet IA’s burden to show a lack of market harm. Taking them at face value, they show at best that the presence of the Works in Suit in IA’s online library correlated, however weakly, with positive financial indicators for the Publishers in other areas. They do not show that IA’s conduct caused these benefits to the Publishers. In any event, IA cannot offset the harm it inflicts on the Publishers’ library ebook revenues, see, e.g., Andy Warhol Found., 11 F.4th at 48; TVEyes, 883 F.3d at 180, by pointing to other asserted benefits to the Publishers in other markets. Nor could those asserted benefits tip the scales in favor of fair use when the other factors point so strongly against fair use." (Case 1:20-cv-04160-JGK-OTW Document 188 Filed 03/24/23 Page 43)</blockquote>Given this kind of reasoning, there is no "proof" that <i>any</i> library could provide that would clearly absolve the library of harm to publishers. That should be okay because "not harming publishers" is not how we should see the role of libraries in our world. Libraries exist for the same reasons that educational institutions exist: to further the abilities of citizens to participate in <a href="https://constitution.congress.gov/browse/article-1/section-8/clause-8/">"science and the useful arts"</a>, as it is called in the constitution. Yet as Dan Cohen says in his article in the <a href="https://www.theatlantic.com/ideas/archive/2023/03/publishers-librarians-ebooks-hachette-v-internet-archive/673560/">Atlantic</a>:<br /><blockquote>On Friday, the judge sided almost entirely with the publishers. The Internet Archive “argues that its digital lending makes it easier for patrons who live far from physical libraries to access books and that it supports research, scholarship, and cultural participation by making books widely accessible on the Internet,” Judge John G. Koeltl wrote in his pointed ruling. “But these alleged benefits cannot outweigh the market harm to the Publishers.” </blockquote>Thus, societal benefits, such as those of libraries and schools, take a back seat to profit. Or should I say "alleged benefits." Today, copyright law creates a basis for the legality of library lending through the <a href="https://en.wikipedia.org/wiki/First-sale_doctrine">first sale doctrine</a>. Some <a href="https://www.copyright.gov/title17/92chap1.html#108">library privileges</a> relating to making copies are included in the US copyright law. But these do not add up to actual <i>support</i> for the work of libraries, only a limitation on culpability as they perform key functions such as preserving cultural materials that have been abandoned by their creators and providing access to recorded culture to all who request it. In the legal regime, libraries are allowed, but not encouraged, to provide a valuable service for society. Judge John G. Koeltl has little regard for that service.<br /><br /><p></p>Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com0tag:blogger.com,1999:blog-3338174527262061848.post-80242306478853159932023-04-06T12:43:00.001-07:002023-04-16T08:21:01.078-07:00Judge's Decision on Internet Archive's Controlled Digital Lending<p>The story is long and complex, so here's about the shortest Q&A summary that I can manage. Remember IANAL (I am not a lawyer), IAAL (I am a librarian). Also, I'm leaving out lots of details here, but provide links so that you can get to them. While this is playing out as a legal question, the societal issues are barely considered. I will try to give some thoughts on those soon.<br /><br /><b>Q: Who sued the Archive?</b><br />A: Four publishers: Hachette Book Group, Inc., HarperCollins Publishers LLC, John Wiley & Sons, Inc., Penguin Random House LLC.<br /><br /><b>Q: What did they sue about?</b><br />A: That the Archive digitized paper books for which the publishers hold the copyright and loaned the digital copies to people.<br /><br /><b>Q: Are these the only publishers whose works the Archive digitized?</b><br />A: Oh, no. There are probably thousands of others.<br /><br /><b>Q: What are the books that are named in the suit?</b><br />A: There are too many to list, but here are a few to give you an idea:<br /></p><ul style="text-align: left;"><li>Elizabeth Gilbert's <i>Eat, Pray, Love: One Woman's Search for Everything Across Italy, India and Indonesia</i> </li><li>Malcolm Gladwell's <i>Blink: The Power of Thinking Without Thinking </i></li><li>C. S. Lewis's <i>The Lion, the Witch, and the Wardrobe</i></li><li>J. D. Salinger's <i>The Catcher in the Rye</i></li><li>Laura Ingalls Wilder's <i>The House on the Prairie</i></li></ul><p>There are many minor works as well, and others whose titles you would recognize.<br />The full list is at: <a href="https://storage.courtlistener.com/recap/gov.uscourts.nysd.537900/gov.uscourts.nysd.537900.1.1.pdf">https://storage.courtlistener.com/recap/gov.uscourts.nysd.537900/gov.uscourts.nysd.537900.1.1.pdf</a><br /><br /><b>Q: What was the Archive's legal defense for its actions?</b><br />A: They argue that digitization is analogous to the kind of time-shifting that is done through technologies like Tivo; it is a sort of "format shift" and therefore is fair use. They also argue that the Archive, as a non-profit library, is providing a lending service like libraries do with hard copies of books. It calls this process of digitizing and lending "Controlled Digital Lending." In Controlled Digital Lending the library treats the original hard copy and the digital copy as a single "thing" and lends either one or the other but not both at a time. This is called the "one-to-one principle" and it is designed to mimic the First Rights law of the US which is the basis for the legality of library lending.<br /><br /><b>Q: How did the court respond?</b><br />A: The judge looked at the <a href="https://www.copyright.gov/title17/92chap1.html#107">four factors</a> of the US copyright law and concluded that the Archive's use was not fair. He accepted the publisher's arguments that the lending of the books competed with the publishers' own digital and physical sales. He also bought the publishers' argument that the Archive, albeit a non-profit, gained status and therefore donations through the book lending service.<br /><br /><b>Q: Are there legal arguments to support Controlled Digital Lending?</b><br />A: Yes, ones have been made. In particular there is the work of Michelle Wu, who wrote <a href="http://www.aallnet.org/mm/Publications/llj/LLJ-Archives/Vol-103/Fall-2011/2011-34.pdf">"Building a Collaborative Digital Collection: A Necessary Evolution in Libraries."</a>. Her initial thesis regarded law libraries and their difficulty in keeping up with the production of legal resources. Later, she was one of a group of legal scholars who developed a more general <a href="https://controlleddigitallending.org/statement/">statement on Controlled Digital Lending</a>. They argue that in this environment of increasing remote access to information, libraries have to be able to move beyond the requirement that users visit a physical space to access materials. And since not all materials have been provided in digital form, libraries need to take on the process of digitization for materials that they hold only in hard copy.<br /><br /><b>Q: Is this the first time that libraries have digitized materials?</b><br />A: No. Libraries have used various technologies, including digitization, to make materials available to disabled users. They also have digitized, faxed, and copied individual journal articles and book sections to satisfy interlibrary loan requests. They rarely have digitized entire books except to preserve rare materials, but those are generally free of copyrights due to their age.<br /><br /><b>Q: So, did the Archive do something wrong?</b><br />A: Possibly. For materials online a copyright holder can issue a "take down" notice, and the recipient is obligated to remove the item from access. The publishers claim that they gave the Archive a list of items to take down, but not all were removed. I haven't seen a statement from the Archive on why that method failed. Then, for about four months, during the beginning of the COVID pandemic in 2020, the Archive eliminated the one-to-one rule and allowed unlimited lending. This was done as a service to offset the fact that during that time many physical libraries were closed to their users, but it was not in keeping with the legal principles that had been laid out for Controlled Digital Lending. </p><p>Another possible error was the digitization of materials for which the publishers have digital versions (ebooks) on offer. This makes the argument that the Archive was competing with the publishers more convincing. Copyright law also views "creative" works more strongly than factual works, and these are publishers of fiction as well as popular non-fiction, types of works that one could see as worthy of maximum copyright protection. Materials intended for research and education (academic journal articles, scientific treatises) are more likely to meet the "purpose" requirement of a fair use assessment. It is quite a bit harder to claim fair use copying for "something fun to read" and the publishers in the suit are all major purveyors of popular reading. </p><p> Continuing on, most libraries have a limited user base: universities serve current students, staff and faculty; public libraries serve residents in their jurisdiction. The Archive was lending materials globally. That latter is both an argument against the Archive, if you are a publisher, and an argument for the Archive, if you support equal access to information. </p><p><b>Q: Didn't we go through this already with Google books?</b></p><p>Not quite. Google never allowed anyone to <i>read</i> its digitized books. It stated that its digitization project was to provide searching within the text of books, and users were only displayed snippets, not the whole book. That was deemed to be fair use by the court. Since then, Google books has mainly been acquiring digital texts provided by publishers, and the amount of visible content is part of the <a href="https://support.google.com/books/partner/answer/3296063">agreement between Google and its book partners</a>.<br /><br /><b>Q: Could a different implementation of Controlled Digital Lending succeed?</b><br />A: Possibly. There are libraries that have partnered with the Archive in this project but were not mentioned in the lawsuit; it is unclear whether they will be able to continue lending their digitized books - although they may have to find another technical solution to the lending service, which is currently run by the Archive. There is also the possibility that a digitization project that had specific service goals, like the one initially proposed by Wu for law libraries, would be easier to defend. Both the Archive and the earlier digitization project, Google Books,
decided that it was expedient to digitize first and ask permission
later. They also both digitized indiscriminately, including old and new,
academic and popular. Google eventually adopted an "opt-in" model in
its publisher relations, although as the search engine of record what it
has to offer is a level of visibility that no one else can provide. The other option is to limit access to books in the public domain,
which cuts off almost the last century of works. <br /><br /><b>Q: What's next?</b><br />A: There will be appeals by the Archive, but if those do not alter the court's view then the Archive will be required to compensate the publishers for its infringement of their rights. Presumably that compensation will be based on some estimated amount that the publishers were damaged. So far I have no seen any actual figures that would be used to make such a determination.<br /><br /></p><h2 style="text-align: left;">Resources:</h2><ul style="text-align: left;"><li><a href="https://controlleddigitallending.org/">The Controlled Digital Lending site</a></li><li><a href="https://www.courtlistener.com/docket/17211300/hachette-book-group-inc-v-internet-archive/?order_by=desc">The many documents in the lawsuit</a> </li><li><a href="https://storage.courtlistener.com/recap/gov.uscourts.nysd.537900/gov.uscourts.nysd.537900.188.0.pdf">The judge's decision </a><br /></li><li><a href="https://authorsguild.org/advocacy/open-library/">The Authors Guild CDL page</a></li><li><a href="https://en.wikipedia.org/wiki/Authors_Guild,_Inc._v._Google,_Inc.">Google books legal decision</a> (from Wikipedia because it has lots of links) </li></ul>Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com0tag:blogger.com,1999:blog-3338174527262061848.post-53889293971491492152023-01-10T10:14:00.000-08:002023-01-10T10:14:34.403-08:00KO is KO'd<p>A library is intended to be a place of organized knowledge. Knowledge organization (KO) takes place in two areas: the shelf and the catalog. In this post I want to address KO in the catalog.</p><h3 style="text-align: left;">Headings</h3><p>KO in the catalog makes use of "headings". Headings are catalog entry points, such as the title of a work or the name of an author. Library catalogs also assign topical headings to their holdings. <br /><br />The "knowledge organization" of the title and author headings consists of alternate versions of those. Alternate forms can be from an unused form (Cornwell, David John Moore) to the used one (Le Carré, John). They can also refer from one form that a searcher may use (Twain, Mark) to a related name that is also to be found in the catalog (Snodgrass, Quintus Curtius). <br /><br />Subject headings are a bit more complex because they also have the taxonomic relationships of broader and narrower concepts. So a broader term (Cooking) can link to a narrower term (Desserts) in the same topic area. Subject headings also have alternate terms and related terms.<br /><br />The way that this KO is intended to work is that each heading and reference is entered into the catalog in alphabetical order where the user will encounter them during a search. <br /><br />Cornwell, David John Moore<br /> see: Le Carré, John<br /><br />Twain, Mark<br /> see also: Snodgrass, Quintus Curtius<br /> <br />Cooking<br /> see narrower: Desserts<br /> see narrower: Frying<br /> see narrower: Menus<br /> <br />It may seem obvious but it is still important to note that this entire system is designed around an alphabetical browse of strings of text. The user was alerted to the alternate terms and the topical structure during the browse of cards in the card catalog, where the alternate and taxonomic entries were recorded for the user to see. Any "switching" from one term to another was done by the user herself who had to walk over to another catalog drawer and look up the term, if she so chose. The KO that existed in the catalog was evident to the user.<br /></p><h3 style="text-align: left;">Automation</h3><p>A database of data creates the ability to search rather than browse. A database search plucks precise elements from storage in response to a query and delivers them to the questioner. The "random access" of that technology has all but eliminated the need to find information through alphabetical order. Before the database there was no retrieval in the sense that we mean today, retrieval where a user is given a finite set of results without intermediate steps on their part. Instead, yesterday's catalog users moved around in an unlimited storehouse of relevant and non-relevant materials from which they had to make choices. <br /><br />In the database environment, the user does not see the KO that may be provided. Even if the system does some term-switching from unused to used terms, the searcher is given the result of a process that is not transparent. Someone searching on "Cornwell, David" will receive results for the name "John Le Carré" but no explanation of why that is the case. Less likely is that a search on "Twain, Mark" will lead the searcher to the works that Twain wrote under the additional alias of "Snodgrass, Quintus Curtius" or that the search on "Cooking" will inform the user that there is a narrower heading for "Menus." A precise retrieval provides no context for the result, and context is what knowledge organization is all about.<br /><br />Answering a question is not a conversation. The card catalog engaged the user in at least a modicum of conversation as it suggested entry headings other than the ones being browsed. It is even plausible that some learning took place as the user was guided from one place in the list to another. None of that is intended or provided with the database search. <br /></p><h3 style="text-align: left;">KW is especially not KO</h3><p>The loss of KO is exacerbated with keyword searching. While one might be able to link a reference to a single-word topic or to a particular phrase, such as "cookery" to "cooking," individual words that can appear anywhere in a heading are even further removed from any informational context. A word like "solar" ("solar oscillations", "solar cars", "orbiting solar observatories") or "management" ("wildlife management", "time management", "library catalog management") is virtually useless on its own, and the items retrieved will be from significantly different topic areas. <br /><br />Keyword searching is very popular because, as one computer science student once told me, "I always get something." The controversy today over mis-information is around the fact that "something" is a context-free deliverable. In libraries, keyword searching helps users retrieve items with complex headings, but the resulting resources may be so different one from the other that the the retrieved set resembles a random selection from the catalog. Note, too, that even the sophisticated search engines are unable to inform their users that broader and narrower topics exist, nor can they translate from words to topics. Words are tools to express knowledge, but keywords are only fragments of knowledge.<br /></p><h3 style="text-align: left;">21st Century Goals</h3><p>I would like to suggest a goal for 21st century librarians, and that is a return to knowledge organization. I don't know how it can be done, but it is essential to provide this as a service to library users who are poorly served by the contextless searches in today's library catalogs. To accomplish this with computer and database technology will probably not make use of the technique of heading assignment of the card catalog. Users might enter the library through a topic map of some type, perhaps. I really don't know. I do know that educating users will be a big hurdle; the facility of typing a few words and getting "something" will be hard to overcome in a world where quick bits of information are not only the norm but all that some generations have ever known. A knowledge system has to be demonstrably better, and that's a tall order.</p>Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com2tag:blogger.com,1999:blog-3338174527262061848.post-60351841129992527222022-11-05T09:51:00.006-07:002022-11-14T10:44:43.127-08:00Cautions on ISBN and a bit on DOI<p>I have been reading through the documents relating to the <a href="https://www.courtlistener.com/docket/17211300/hachette-book-group-inc-v-internet-archive/">court case</a> that Hachette has brought against the Internet Archives "controlled digital lending" program. I <a href="https://kcoyle.blogspot.com/2021/03/digitization-wars-redux.html">wrote briefly</a> about this before. In this recent reading I am once again struck by the use and over-use of ISBNs as identifiers. Most of my library peeps know this, but for others, I will lay out the issues and problems with these so-called "identifiers".</p><h3 style="text-align: left;">"BOOK"</h3><p>The "BN" of the ISBN stands for "BOOK NUMBER." The "IS" is for "INTERNATIONAL STANDARD" which was issued by the International Standards Organization, whose documents are unfortunately paywalled. But the un-paywalled page defines the target of an ISBN as:</p><p></p><blockquote>[A] unique international identification system for each product form or
edition of a separately available monographic publication published or
produced by a specific publisher that is available to the public.</blockquote><p></p><p>What isn't said here in so many words is that the ISBN does not define a specific content; it defines a salable product instance in the same way that a UPS code is applied to different sizes and "flavors" of Dawn dish soap. What many people either do not know or may have forgotten is that every book product is given a different ISBN. This means that the hardback book, the trade paperback, the mass-market paperback, the MOBI ebook, the EPUB ebook, even if all brought to market by a single publisher, all have different ISBNs. </p><p>The word "book" is far from precise and it is a shame that the ISBN uses that term. Yes, it is applied to the book trade, but it is not applied to a "book" except in a common sense of that word. When you say "I read a book" you do not often mean the same thing as the B in ISBN. Your listener has no idea if you are referring to a hard back or a paperback copy of the text. It would be useful to think of the ISBN as the ISBpN - the International Standard Book product Number.</p><p>Emphasizing the ISBN's use as a product code, bookstores at one point were assigning ISBNs to non-book products like stuffed animals and other gift items. This was because the retail system that the stores used required ISBNs. I believe that this practice has been quashed, but it does illustrate that the ISBN is merely a bar code at a sales point.<br /></p><h3 style="text-align: left;">1970</h3><p>The ISBN became a standard product number in the book trade in 1970, in the era when the Universal Product Code (UPC) concept was being developed in a variety of sales environments. This means that every book product that appeared on the market before that date does not have an ISBN. This doesn't mean that a text from before that date cannot have an ISBN - as older works are re-issued for the current market, they, too, are given ISBNs as they are prepared for the retail environment. Even some works that are out of copyright (pre-1925) may be found to have ISBNs when they have been reissued. </p><p>The existence of an ISBN on the physical or electronic version of a book tells you nothing about its copyright status and does not mean that the book content is currently in print. It has the same meaning as the bar code on your box of cereal - it is a product identifier that can be used in automated systems to ring up a purchase. </p><h3 style="text-align: left;">The Controlled Digital Lending Lawsuit</h3><p>
</p><p style="margin: 0in; text-align: left;"><span style="font-size: small;"><span style="font-family: inherit;">The lawsuit between a group of publishers led by Hachette and the Internet Archive is an example of two different views: that of selling and that of reading. <br /></span></span></p><p style="margin: 0in; text-align: left;"><span style="font-size: small;"><span style="font-family: inherit;"> </span></span></p><p style="margin: 0in; text-align: left;"><span style="font-size: small;"><span style="font-family: inherit;">In the lawsuit the publishers
quantify the damage done to them by expressing the damage to them in terms of numbers of </span></span>ISBNs<span style="font-size: small;"><span style="font-family: inherit;">. This Implies
that the lawsuit is not including back titles that are pre-ISBN. Because the
concern is economic, items that are long out of print don't seem to be included in the
lawsuit.</span></span></p><p style="text-align: left;"><span style="font-size: small;"><span style="font-family: inherit;">
</span></span></p><p style="margin: 0in; text-align: left;"><span style="font-size: small;"><span style="font-family: inherit;">The difference
between the book as product and the book as content shows up in how </span></span>ISBNs<span style="font-size: small;"><span style="font-family: inherit;"> are
used. The <a href="https://www.courtlistener.com/docket/17211300/100/2/hachette-book-group-inc-v-internet-archive/">publisher’s expert</a> notes that many metadata records at the archive
have multiple </span></span>ISBNs<span style="font-size: small;"><span style="font-family: inherit;"> and surmises that the archive is adding these to the
records. What this person doesn’t know is that library records, which the
archive is using, often contain </span></span>ISBNs<span style="font-size: small;"><span style="font-family: inherit;"> for multiple book products which the
libraries consider interchangeable. The library user is seeking specific
content and is not concerned with whether the book is a hard back, has library
binding, or is one of the possible soft covers. The “book “ that the library
user is seeking is an information vessel.</span></span></p><p style="text-align: left;"><span style="font-size: small;"><span style="font-family: inherit;">
</span></span></p><p style="margin: 0in; text-align: left;"><span style="font-size: small;"><span style="font-family: inherit;">It is the practice in
libraries, where there is more than one physical book type available, to show
the user a single metadata record that doesn’t distinguish between them. The
record may describe a hard bound copy even though the library has only the
trade paperback. This may not be ideal but the cost-benefit seems defensible.
Users probably pay little attention to the publication details that would
distinguish between these products. </span></span></p><p style="margin: 0in; text-align: left;"><span style="font-size: small;"><span style="font-family: inherit;"> </span></span></p><table align="center" cellpadding="0" cellspacing="0" class="tr-caption-container" style="margin-left: auto; margin-right: auto;"><tbody><tr><td style="text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjXVJ_XDeeJbEYA0YgYsx1MIvSujv6dgMaLKIdPaqT31gTiBx8wMypsh43vpiIh93nyCNZZ-U2YKLPj_L8ywI5aZtcmbzJHTylQfeUqbzfE3JFc-VRRIM6z86LzUKKe-GL9BLllMKWnTaA7JKlS5XIxXkdaeHp8CExGqE0Ii3hQI2L_VniUELau1rgCTA/s296/Screen%20Shot%202022-11-05%20at%209.27.10%20AM.png" style="margin-left: auto; margin-right: auto;"><img border="0" data-original-height="164" data-original-width="296" height="164" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjXVJ_XDeeJbEYA0YgYsx1MIvSujv6dgMaLKIdPaqT31gTiBx8wMypsh43vpiIh93nyCNZZ-U2YKLPj_L8ywI5aZtcmbzJHTylQfeUqbzfE3JFc-VRRIM6z86LzUKKe-GL9BLllMKWnTaA7JKlS5XIxXkdaeHp8CExGqE0Ii3hQI2L_VniUELau1rgCTA/s1600/Screen%20Shot%202022-11-05%20at%209.27.10%20AM.png" width="296" /></a></td></tr><tr><td class="tr-caption" style="text-align: center;"><i>From a single library metadata record</i><br /></td></tr></tbody></table><span style="font-size: small;"><span style="font-family: inherit;"><br /></span></span><p></p><p style="margin: 0in; text-align: left;"><span style="font-size: small;"><span style="font-family: inherit;"> </span></span></p><p style="margin: 0in; text-align: left;"><span style="font-size: small;"><span style="font-family: inherit;">Where libraries do differentiate is between
forms that require special hardware or software. Even here however the </span></span>ISBN<span style="font-size: small;"><span style="font-family: inherit;">
cannot be used for the library’s purpose because services that manage these
materials can provide the books in the primary digital reading formats based off a
single metadata record, even though each ebook format is assigned its own </span></span>ISBN for the purpose of sales<span style="font-size: small;"><span style="font-family: inherit;">.</span></span></p><p style="text-align: left;"><span style="font-size: small;"><span style="font-family: inherit;">
</span></span></p><p style="margin: 0in; text-align: left;"><span style="font-size: small;"><span style="font-family: inherit;">The product view is
what you see on Amazon. The different products have different prices which is
one way they are distinguished. A buyer can see the different prices for hard
copy, paperback, or kindle book, and often a range of prices for used copies. Unlike
the library user, the Amazon customer has to make a choice, even if all of the
options have the same <i>content</i>. For sales to be possible, each of the products has its own ISBN. </span></span></p><p style="margin: 0in; text-align: left;"><span style="font-size: small;"><span style="font-family: inherit;"></span></span></p><table align="center" cellpadding="0" cellspacing="0" class="tr-caption-container" style="margin-left: auto; margin-right: auto;"><tbody><tr><td style="text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiKNmJ3M1wNFnprrgeA1oofDugV9EO1VXfqrLAr4dC1tqIhoid3NbX2pZbGjQoXqFXR0Wxqfk2l4xb03-AoMYxNMck_fWcccs2_-9c-DglewZDtzTd2XWcJh7CGkoD3_Ou-3FhNM1QM8EBmL4PupCOreXMJVNncyyYzjkHsHSOSSU7Y2rvPygcHcAUEjw/s645/Screen%20Shot%202022-11-05%20at%209.35.33%20AM.png" style="margin-left: auto; margin-right: auto;"><img border="0" data-original-height="144" data-original-width="645" height="101" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiKNmJ3M1wNFnprrgeA1oofDugV9EO1VXfqrLAr4dC1tqIhoid3NbX2pZbGjQoXqFXR0Wxqfk2l4xb03-AoMYxNMck_fWcccs2_-9c-DglewZDtzTd2XWcJh7CGkoD3_Ou-3FhNM1QM8EBmL4PupCOreXMJVNncyyYzjkHsHSOSSU7Y2rvPygcHcAUEjw/w455-h101/Screen%20Shot%202022-11-05%20at%209.35.33%20AM.png" width="455" /></a></td></tr><tr><td class="tr-caption" style="text-align: center;"><i>Different products have different prices</i><br /></td></tr></tbody></table><span style="font-size: small;"><span style="font-family: inherit;"><br /></span></span><p></p><p style="margin: 0in; text-align: left;"><span style="font-size: small;"><span style="font-family: inherit;"><br /></span></span></p><p style="margin: 0in; text-align: left;"><span style="font-size: small;"><span style="font-family: inherit;">Counting ISBNs may be the correct quantifier for the publishers, but they feature only minimally in the library environment. Multiple ISBNs on a single library metadata record is not an attempt to hide publisher products by putting them together; it's good library practice for serving its readers. Users coming to the library with an ISBN will be directed to the content they seek regardless of the particular binding the library owns. Counting the ISBNs in the Internet Archive's metadata will not be a good measure of the number of "books" there using the publisher's definition of "book."<br /></span></span></p><p style="margin: 0in; text-align: left;"><span style="font-size: small;"><span style="font-family: inherit;"><br /></span></span></p><h3 style="margin: 0in; text-align: left;"><span style="font-size: small;"><span style="font-family: inherit;">Digital Object Identifier (DOI)</span></span></h3><p style="margin: 0in; text-align: left;"><span style="font-size: small;"><span style="font-family: inherit;"><br /></span></span></p><p style="margin: 0in; text-align: left;"><span style="font-size: small;"><span style="font-family: inherit;">I haven't done a deep study of the use of <a href="https://www.doi.org/">DOIs</a>, but again there seems to be a great enthusiasm for the DOI as an identifier yet I see little discussion of the limitations of its reach. DOI began in 2000 so it has a serious time limit. Although it has caught on big with academic and scientific publications, it has less reach with social sciences, political writing, and other journalism. Periodicals that do not use DOIs may well be covering topics that can also be found in the DOI-verse. Basing an article research system on the presence of DOIs is an arbitrary truncation of the knowledge universe.<br /></span></span></p><p style="margin: 0in; text-align: left;"><span style="font-size: small;"><span style="font-family: inherit;"> </span></span></p><h3 style="margin: 0in; text-align: left;"><span style="font-size: small;"><span style="font-family: inherit;">The End <br /></span></span></h3><p style="margin: 0in; text-align: left;"><span style="font-size: small;"><span style="font-family: inherit;"> </span></span></p><p style="margin: 0in; text-align: left;"><span style="font-size: small;"><span style="font-family: inherit;">Identifiers are useful. Created works are messy. Metadata is often inadequate. As anyone who has tried to match up metadata from multiple sources knows, working without identifiers makes that task much more difficult. However, we must be very clear, when using identifiers, to recognize what they identify.<br /></span></span></p><p style="text-align: left;"><span style="font-family: inherit;">
</span></p><p><br /></p>Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com0tag:blogger.com,1999:blog-3338174527262061848.post-33193414050281632542022-06-27T17:31:00.003-07:002022-07-01T09:05:02.536-07:00The OCLC v Clarivate Dilemma<p>OCLC has <a href="https://www.oclc.org/content/dam/oclc/protectworldcat/06-13-2022-OCLC-MetaDoor-Complaint.pdf" target="_blank">filed suit</a> against the company Clarivate which owns Proquest and ExLibris. The suit focuses on a metadata service proposed by Ex Libris called "MetaDoor." MetaDoor isn't a bibliographic database à la WorldCat, it is a peer-to-peer service that allows its users to find quality records in the catalog systems of other libraries. ("MetaDoor" is a terrible name for a product, by the way.)<br /><br />What seems to specifically have OCLC's dander up is that Ex Libris states that it will allow any and all libraries, not just its Alma customers, to use this service for free. As the service does not yet exist it is unknown how it could affect the library metadata sharing environment. It may succeed, it may fail. If it succeeds, the technology that Ex Libris develops will be a logical next step in bibliographic data sharing, but its effect on OCLC is hard to predict.</p><p></p><h3 style="text-align: left;">Yesterday's and Today's Technology<br /></h3><p>WorldCat is yesterday's technology: a huge, centralized database. Peer-to-peer sharing of bibliographic records has been available since the 1980's with the development of the <a href="https://en.wikipedia.org/wiki/Z39.50">Z39.50 protocol</a>, and presumably a considerable amount of sharing over that protocol has been used by libraries to obtain records from other libraries. Over the years many programs and systems have been developed to make use of Z39.50 and the protocol is built in to library systems, both for obtaining records and for sharing records. <br /><br />The actual extent of peer-to-peer sharing of bibliographic records already today does not seem to be known, although I did only a brief amount of research looking for that information. It is definitely in use in library environments where participation in OCLC is unaffordable; articles vaunt its use in Russia, India, Korea, and other countries. It is built into the open source library system Koha that is aimed at those libraries that are priced out of the mainstream library systems market. Where libraries have known peers, such as the national library of a country, peer-to-peer makes good sense. <br /><br />What OCLC's centralized database has that peer-to-peer lacks (at least to date) is consolidated library holdings information. As <a href="https://twitter.com/banerjek/status/1539372340613591040?s=20&t=v8B-lQ5293d-XmvCp3GGvw">Kyle Banerjee said</a> on Twitter, the real value in WorldCat is the holdings. This is used by interlibrary loan systems, and it is what appears on the screen when you do a WorldCat search. Cleverly, OCLC has recorded the geographical location of all of its holding libraries and can give you a list of libraries relative to your location. In the past this type of service was only available through a central database, but we may have arrived at point where peer-to-peer could provide this as well.<br /><br />A couple of other things before I look at some specific points in the lawsuit. One is that WorldCat is not the only bibliographic database used for sharing of metadata. Some smaller library companies also have their own shared databases. These are much smaller than WorldCat and the libraries that use them generally are 1) unable to afford OCLC's member fees and 2) do not have need of the depth or breadth of WorldCat's bibliographic data. For example, the CARL database from TLC company has a database of <a href="https://tlcdelivers.com/data-services/">77 million</a> records, many less than worldCat's over 500 million. Even the Library of Congress catalog is only 20 million strong. The value for some libraries is that WorldCat contains the long tail; for others, that long tail is not needed. It's the difference between the Harvard library and your local public library. Harvard may well have need for metadata for a Lithuanian poetry journal, your local public library can do just fine with a peer database of popular works published in the US. <br /><br />And another: we're slowly moving to a less "thing"-based world to a "data"-based world. Yes, scholars still need books and journals, but increasingly our information seeking returns tiny bites, not big thoughts. You can rue that, but I think it's only going to get worse. It's like the difference between a Ken Burns 10-part documentary on the Civil War and TikTok. The metadata creation activity for the deep thoughts of books and articles is not viable for YouTube, Instagram, TikTok or even Facebook. Us "book people" are hanging on to a vast repository that is less and less looking forward and more and more becoming dusty and crusty. We don't want to lose that valuable archive, but it is hard to claim that we are not a fading culture.<br /><br />OK, to the lawsuit.</p><h3 style="text-align: left;">What is the Nut of this Case?</h3><p>OCLC claims in its suit that
Clarivate is undertaking MetaDoor as a malicious act, targeting WorldCat
with a desire to destroy it. I don't think you need to be malicious to
come up with a project to create an efficient system for sharing
bibliographic records. Creating a shared database at this time is simply
a logical need for any data service. </p><p>The main fact behind OCLC's suit is that uploading library catalog bibliographic records to
MetaDoor is a violation of the libraries' contracts with OCLC, and that Clarivate/Ex Libris is encouraging libraries to violate their contracts. As
Clarivate has no such contract with OCLC, the suit uses terms like "conspiracy" and a lot of "tortious" to describe that Clarivate/Ex Libris is
breaking some law of competition by encouraging OCLC customers to violate their contracts. <br /></p><p>I'm not sure how
that will play in court but you can see on the Clarivate site that one
of their main areas of expertise is in intellectual property around
data. Regardless of the outcome of this suit we may get to see some interesting
arguments around data ownership. It's still a wide-open area where some
smart discussion would be very welcome.</p><h3 style="text-align: left;">The ILS Market<br /></h3><p>The lawsuit complains that Clarivate has become the largest player in the ILS market through its purchase of systems like Ex Libris and ProQuest. (It isn't clear to me how "large" is defined here.) It also bemoans the consolidation of the library market. The library market is hardly unique in this; consolidation of this type is a normal course of things in our barely-regulated capitalism. It is, as always, hard to understand just what Clarivate owns because Clarivate owns Proquest which owns Ex Libris which owns Innovative Interfaces which owns SkyRiver and VTLS, among others. The number of players in the library market, which once was a handful of independent companies, is shrinking at a rapid rate, and this has been a worry in the library world now for decades.</p><p>On its web site Clarivate presents itself as a research data and
analytics company. It includes Proquest and Web of Science in its list of offerings, but
interestingly makes no mention of Ex Libris. I've always wondered why anyone with any business sense would want to enter the library cataloging systems market. In fact, Clarivate inherited Ex Libris when it purchased Proquest, and the <a href="https://clarivate.com/news/clarivate-successfully-completes-acquisition-of-proquest/">Clarivate press release</a> upon acquiring Proquest makes no mention of Ex Libris or other library systems. </p><p>Speaking of market consolidation, one must remember that at one time OCLC had two rather large competitors in the library cataloging market: the Western Library Network and Research Libraries Information Network. OCLC purchased both of these, and they then ceased to exist. That was itself a consolidation that concerned many because at the time few library cataloging systems provided a significantly large database to support the cataloging activity. Also, take a gander at this chart from <a href="https://librarytechnology.org/vendor/oclc/">Marshall Breeding's Library Tech Guides</a> that shows the "mergers and acquisitions" of OCLC:<br /></p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjpJ4b-9IQhC3q5pIXsbd6FRzIMyQ55_lTi7sh1Q96xuPFjSrslAdIowsQGJIBdMIOptBdgWA7dQrENEjmBBHr6SdgY5Tv0h85M9F6rBXAxCReqQeTAu1BYKU6MutBfS235tTm_OFuKKMz2TYSwH8FeA2hZ7NNjky0LMJaYy_IMejM275NAUnkiZKgLNg/s1971/oclcacquisitions.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="1114" data-original-width="1971" height="216" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjpJ4b-9IQhC3q5pIXsbd6FRzIMyQ55_lTi7sh1Q96xuPFjSrslAdIowsQGJIBdMIOptBdgWA7dQrENEjmBBHr6SdgY5Tv0h85M9F6rBXAxCReqQeTAu1BYKU6MutBfS235tTm_OFuKKMz2TYSwH8FeA2hZ7NNjky0LMJaYy_IMejM275NAUnkiZKgLNg/w381-h216/oclcacquisitions.jpg" width="381" /></a></div><br /><p>(more readable on Marshall's site, so hop over there fore details)<br /></p><h3 style="text-align: left;">What is a WorldCat record?</h3><p>The lawsuit speaks of the "theft" of WorldCat records by Ex Libris for their MetaDoor product (which isn't well explained as the records will be voluntarily offered by the participating libraries). The peer-to-peer action of MetaDoor, however, does not touch the WorldCat database directly. As I understand it from the Ex Libris web site, libraries using the Ex Libris system agree to have that system harvest records from their database. Information from those records will be indexed in MetaDoor but the records themselves will not stored there. Users of MetaDoor will discover records they need for cataloging through MetaDoor, and the records will be retrieved from the library system holding the record. Without a doubt, some of those records will have been downloaded by libraries during cataloging on OCLC. The lawsuit refers to these as "WorldCat records." <br /><br />Here's the hitch: these are records are distributed among individual library databases. Each MARC record is a character string in which any part of that string can be modified using software written for that purpose. That software may be part of the library catalog system, or it may be standalone software like the open software MARCedit. Other software, like Open Refine, has been incorporated into batch workflows for MARC records to make changes to records. Basically, the records undergo a lot of changes, both the "enhancements" in WorldCat that the lawsuit refers to but also an unknown quantity of modifications once individual libraries obtain them. <br /></p><p>Note that some libraries do not use OCLC and therefore have no WorldCat
records, and many libraries have multiple sources of bibliographic data. It simply isn't possible to say "all your MARC belong to us." It's much more complicated than that. Although there is nominally both provenance and versioning data in the MARC records, these fields are as editable as all others. In addition, some systems ignore these and do not attempt to update those details as the records are edited. This means that there is no way to look at a record in a library database and determine precisely from where it was originally obtained prior to being in that database. If library A uses OCLC to create a catalog record and library B (not an OCLC cataloging customer) uses its catalog system's Z39.50 option to copy that record from Library A, modifying the record for its own purposes, then library C obtains the record from Library B ... well, you see the problem. These records may flow throughout the library catalog universe, losing their identity as WorldCat records with each step.</p><p>OCLC appears to claim in its suit that the OCLC number confers some kind of ownership stamp on the records. In one of the later paragraphs of a very insightful <a href="https://scholarlykitchen.sspnet.org/2022/06/22/oclc-sues-clarivate-over-the-new-metadoor-platform/">Scholarly Kitchen blog post</a>, Todd Carpenter reminds us that OCLC has not claimed restrictions on the identification number. Also, like everything else in the MARC record, that number can be deleted, modified, or added to a record at the whim of the cataloger. (OK, I admit that "whim" and "cataloger" probably shouldn't be used in the same sentence.) </p><p>Rather than flinging lawsuits around, it would be very interesting to use that money to hire one of those people who looks out 20 years to tell you what the environment will be and what you should be investing in today. I can cover a certain amount of the past, but the future is a fog to me. I hope someone has ideas.</p><p></p><p>-----</p><p>As with many lawsuits, there's a lot of flinging documentation back and forth. Check out <a href="https://www.courtlistener.com/docket/63381226/oclc-online-computer-library-center-inc-v-clarivate-plc/">this site</a> to keep an eye on things. I welcome recommendations of other resources.<br /><br /></p>Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com0tag:blogger.com,1999:blog-3338174527262061848.post-50574194896815378782022-01-26T12:17:00.002-08:002022-01-26T12:42:27.042-08:00What's in a Name?<p><i>This is an essay about the forms of names and their representation in metadata. It is not by any means complete, nor am I an expert in this very complex area. These are my observations and a few suggestions for future work. All comments welcome.</i></p><p><i>[Because this is huge, and printing from here is oddly difficult, here's a <a href="http://kcoyle.net/whatsinaname.pdf">PDF</a>.]</i><br /></p><p>If you do anything online, and surely you do, you have filled in countless forms with your name and address. Within the Western and English-speaking world, these have some minor (and occasionally annoying) variations. You might be asked for a first name and last name, or a given name and a family name, or just a name in a particular order.</p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh7o4yh0Kv_vDvWkTRPt3D9dPKRNYaGcAZL7EAWrkLGLF5biS_ilavPa5xYY1xLDhUDyjqGnRELb2Gl96mbhHTWYts7pv4XnB-54Q4ClfvBHxAymkrFzmhn9HHnzZZ1i2wE4D0FOROlase5/s1064/Screen+Shot+2021-11-27+at+10.19.43+AM.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="120" data-original-width="1064" height="22" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh7o4yh0Kv_vDvWkTRPt3D9dPKRNYaGcAZL7EAWrkLGLF5biS_ilavPa5xYY1xLDhUDyjqGnRELb2Gl96mbhHTWYts7pv4XnB-54Q4ClfvBHxAymkrFzmhn9HHnzZZ1i2wE4D0FOROlase5/w200-h22/Screen+Shot+2021-11-27+at+10.19.43+AM.png" width="200" /></a></div><br /><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj4RXoSfvb4obDxSVREk0qtn0FB6f4qnLW1Mg-zfUaKI6gDxbvO9W_HW-_RHw73L9VWpyPZjihIcNBWWs4xuIXbHy9dbzpq3SQ0X3dAO9sWpC01tQx5ughH-FKZTr_CZgKN7NPt50D_tSUR/s836/Screen+Shot+2021-11-27+at+10.22.48+AM.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="346" data-original-width="836" height="132" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj4RXoSfvb4obDxSVREk0qtn0FB6f4qnLW1Mg-zfUaKI6gDxbvO9W_HW-_RHw73L9VWpyPZjihIcNBWWs4xuIXbHy9dbzpq3SQ0X3dAO9sWpC01tQx5ughH-FKZTr_CZgKN7NPt50D_tSUR/s320/Screen+Shot+2021-11-27+at+10.22.48+AM.png" width="320" /></a></div><p>There are variations, of course. Some recognize the practice of giving a person a "middle" name, that is a second, and perhaps secondary, additional name.<br /></p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhi7U5vkEydyeDfecpwqHLBorR1KmpRL6Ty88g8NEuKumFdg9yJhQccGaVzxg4gJqVYRlecRpISQv4nVpzBm_wXrmBkQuf7H-rF_Pc4ZCZWh7SGu2WDQYemFk6tRz-4AyJFKCqYXHfQhN1d/s1564/Screen+Shot+2021-11-27+at+11.09.40+AM.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="148" data-original-width="1564" height="39" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhi7U5vkEydyeDfecpwqHLBorR1KmpRL6Ty88g8NEuKumFdg9yJhQccGaVzxg4gJqVYRlecRpISQv4nVpzBm_wXrmBkQuf7H-rF_Pc4ZCZWh7SGu2WDQYemFk6tRz-4AyJFKCqYXHfQhN1d/w417-h39/Screen+Shot+2021-11-27+at+11.09.40+AM.png" width="417" /></a></div><p>Because these forms are often used in commercial sites and the companies wish to have a polite relationship with their customers, you might be asked about your preferred form of address. </p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiaTuXYwVmZvnNIB61hhX-MhhjD0sUjQCbLlVTmI8z4v0acfSsNvUYo64buq1Tt46mtdcfXzbMIwpIH2QDAokNKeV8zZTkn0PUTrWrNbYeoY_KffWMnsDhmrUdtwpb8ysJMGTTPufRX4Hge/s310/Screen+Shot+2021-11-27+at+10.31.58+AM.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="308" data-original-width="310" height="171" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiaTuXYwVmZvnNIB61hhX-MhhjD0sUjQCbLlVTmI8z4v0acfSsNvUYo64buq1Tt46mtdcfXzbMIwpIH2QDAokNKeV8zZTkn0PUTrWrNbYeoY_KffWMnsDhmrUdtwpb8ysJMGTTPufRX4Hge/w172-h171/Screen+Shot+2021-11-27+at+10.31.58+AM.png" width="172" /></a></div><p>These forms of address have cultural significance, and the list itself can reveal quite a bit about a culture. This is the list from the British Airways site:</p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgftsDruUllCDPLvenaG3w6Jjo9l9T_HbE49lPeyElGtX3uBloFzmWUTxWpR2k1PmG3brjxJnJV-2NvQPcFWkNSR_HXtEQB2PrM6Q97So0u2vhNtH8WPKqpzZFoChBrt5Z6Sy8qCwwhH-XH/s1142/Screen+Shot+2021-11-27+at+10.28.01+AM.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="820" data-original-width="1142" height="230" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgftsDruUllCDPLvenaG3w6Jjo9l9T_HbE49lPeyElGtX3uBloFzmWUTxWpR2k1PmG3brjxJnJV-2NvQPcFWkNSR_HXtEQB2PrM6Q97So0u2vhNtH8WPKqpzZFoChBrt5Z6Sy8qCwwhH-XH/s320/Screen+Shot+2021-11-27+at+10.28.01+AM.png" width="320" /></a></div><p>We'll come back to some of these below.</p><p>The above examples come from commerce sites. The use of names at those sites are mostly social. Even on a site like a bank, the name has only a minor role in regards to identification because security relies on user names, passwords, and two-factor identification. Names themselves are poor identifiers because they are far from unique across a population. Even if you think you have an unusual name, you will find others with your name in the vastness of the Internet.*<br /></p><p>If you think about times that you've been on the phone with some bank or service, they invariably ask you to provide a telephone number, an email address, or a unique identifier like a social security number as a way to identify you. Only after they have located a record with that identifier do they use your name as both a confirmation that you've given (and they've entered) the correct number, but also so that they can cheerily refer to you by your name.<br /></p><h2 style="text-align: left;">Names in Cultural Heritage</h2><p>Where commercial organizations use names to effect a relationship with their current customers, cultural heritage institutions have a different set of needs. They often cover not only names of modern persons but persons worldwide and of previous eras. An organization must be able to encode this full range of names in a way that is useful today but that is, to the extent possible, faithful to the cultural and historical context of the person. Royalty, religious figures, even characters in mythology all have a very tender place in their respective cultures. To treat them otherwise is to dismiss their cultural importance. You wouldn't want to provide metadata for <a href="https://en.wikipedia.org/wiki/Pope_Benedict_XVI" target="_blank">Benedict XVI</a> without also including that his title and his role in the church is "Pope". You most certainly would not simply name him "Joseph Ratzinger" unless you were giving a very specific, pre-Pope, context. I don't know what name Queen Elizabeth II would provide when signing up
for an Amazon account ("Elizabeth Windsor"?) as there is unlikely to be an input box
appropriate for her royal name, but culturally and historically she is
<a href="https://en.wikipedia.org/wiki/Elizabeth_II">Elizabeth II</a>, Queen of Great Britain. <br /></p><p>There is also the question of giving people their due rank in whatever hierarchy the particular culture values. As you can see with the example above for the list of the titles offered by British Airlines, whereas US-based airlines limit the titles to Mr., Mrs., Ms. and Dr., that titles of nobility are important in the UK. We can presume that to "mis-title" a person would be a social <i>faux pas</i> in most cultures, but there is also a historical context included in titles that one would not want to lose.</p><h2 style="text-align: left;">The "firstname, lastname" Problem</h2><p>Not all names fit the "firstname, lastname" model. A primary reason to identify these parts of names is to support displays in alphabetical order by the "last name". This assumes that the last name is a <a href="https://en.wikipedia.org/wiki/Surname">family name</a>, and that common usage is to gather together all persons with that family name in a display. In reality, this singular "family name" is only one possible name pattern. </p><p>As the term "family name" implies, this positions a person within a group of persons with a particular relationship. In the dominant Western world, the name is paternal and denotes a line of inheritance. But this is by no means the only name pattern that exists. There are cultures where the child's name includes the family names of both the mother and the father, and sometimes other ancestors in the family line. This is how Juan Rodríguez y García-Lozano and María de la Purificación Zapatero Valero, have a son named <a href="https://en.wikipedia.org/wiki/Jos%C3%A9_Luis_Rodr%C3%ADguez_Zapatero">José Luis Rodríguez Zapatero</a>. Treating "Rodríguez Zapatero" as the family name would not bring together the alphabetical entries of the father and son. <br /></p><p>There are other cultures that have a given name and a <a href="https://en.wikipedia.org/wiki/Patronymic">patronymic</a>. While a patronymic may look like a family name, it is not. The singer <a href="https://en.wikipedia.org/wiki/Bj%C3%B6rk">Björk</a> may have seemed to be using a single name as part of her art, like Cher or Madonna, but in fact in the Icelandic culture persons are known by a single name. When a more precise designation is needed, that name is enhanced with a name based on the given name of their father. In this case, Björk has a more "official" name of<span style="font-size: small;"> </span><span style="font-size: small;">Björk Guðmundsdótti</span>r, which is "Björk daughter of <span style="font-size: small;">Guðmundur". Her father's name was </span><span style="font-size: small;">Guðmundur Gunnarsson, he being the son of Gunnar. The author </span><span style="font-size: small;"><a href="https://en.wikipedia.org/wiki/Arnaldur_Indri%C3%B0ason">Arnaldur Indriðason</a><b> </b>is "Arnaldur the son of </span><span style="font-size: small;"><span style="font-size: small;">Indriði." </span>In this practice, creating an order based on the patronymic would result in just a jumble of individual parental names, and persons are almost always called solely by their "first-and-only" name. <br /></span></p><p><span style="font-size: small;">Yet another exception to the firstname/lastname conundrum relates to the names of royalty as mentioned above. <a href="https://en.wikipedia.org/wiki/Charles,_Prince_of_Wales">Charles, Prince of Wales</a> is the son of Elizabeth II. Their names do not connect them which is somewhat ironic given how important family relationships are to royal lineage. Both are of the house of Windsor but you wouldn't know that from their names. Like a Pope, the cultural or political position in these cases outweighs the personal. In addition, the title by which someone is officially known can change over time, making identification even more confusing, with titles being inherited or bestowed as circumstances change. Some people hold a plethora of titles: in addition to Prince of Wales, Charles is Earl of Chester, Duke of Cornwall, Duke of Rothesay, Earl of Merioneth and Baron Greenwich. This is as bad as the name proliferation in Russian novels, and just as confusing.</span></p><p><span style="font-size: small;">And there are the "one name" instances. </span> We have historical figures with only a
single name ("Homer", "Aesop") but there are also current cultures in which
members have only one name.</p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhZ0C3Gm-6TzvuWOTCacs6jfr7AN0uIkP998-XXkk2idlabdxZFn0lQAecpPtEbHn5b_hyphenhyphenVP887H6-Zhx5gO1jcNIOwLKv799mA1wZkFyRd8MewxNO2bs2gs4FAhU10DTh0KTqUOXIKjPKW/s623/Screen+Shot+2021-11-02+at+6.18.51+AM.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="98" data-original-width="623" height="50" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhZ0C3Gm-6TzvuWOTCacs6jfr7AN0uIkP998-XXkk2idlabdxZFn0lQAecpPtEbHn5b_hyphenhyphenVP887H6-Zhx5gO1jcNIOwLKv799mA1wZkFyRd8MewxNO2bs2gs4FAhU10DTh0KTqUOXIKjPKW/s320/Screen+Shot+2021-11-02+at+6.18.51+AM.png" width="320" /></a></div><br /><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiNFzUp0bnSDJS1SbdN0cjbbVFMhlLhyX0tSAxwnyqut9AMwLRthIqq_aOqvxkxiacyRwmKpZ9O6miUDcnDK5MnCLUagyN5eucHDnhjXLk-MdRdnrBxTBQ2gKnMYDf8uU7TEPl5lkEfi7Rz/s623/Screen+Shot+2021-11-02+at+6.20.27+AM.png" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="125" data-original-width="623" height="64" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiNFzUp0bnSDJS1SbdN0cjbbVFMhlLhyX0tSAxwnyqut9AMwLRthIqq_aOqvxkxiacyRwmKpZ9O6miUDcnDK5MnCLUagyN5eucHDnhjXLk-MdRdnrBxTBQ2gKnMYDf8uU7TEPl5lkEfi7Rz/s320/Screen+Shot+2021-11-02+at+6.20.27+AM.png" width="320" /></a></div><p><span style="font-size: small;"> </span></p><p style="text-align: left;"><span style="font-size: large;"><span style="font-size: small;">Any metadata that strictly requires both a given name and a family name will be unable to accommodate these and it</span></span><span style="font-size: large;"><span style="font-size: small;"> is not unusual for people
with only one name to be required to provide a second name to conform
to the given/family name expectation in other cultures. There may even
be local traditions for how one invents such a name. Yet they would not
use that invented name in their own home country. <br /></span></span></p><h2 style="text-align: left;"><span style="font-size: large;">Names and Language</span></h2><p style="text-align: left;"><span style="font-size: small;">It is hard to separate language from culture, but there are some name situations in which the name is translated into the "receiving" language. Catherine (the Great) is Catherine in French, Caterina in Italian, etc. The same is true of Popes:</span></p><p style="margin-left: 40px; text-align: left;"><span style="font-size: small;">Papa Franciscus (Latin)</span></p><p style="margin-left: 40px; text-align: left;"><span style="font-size: small;">Papa Francesco (Italian)</span></p><p style="margin-left: 40px; text-align: left;"><span style="font-size: small;">Papa Francisco (Spanish)</span></p><p style="margin-left: 40px; text-align: left;"><span style="font-size: small;">Pope Francis (English)</span></p><p><span style="font-size: small;">Another twist is that scientists and other cognoscenti of the late medieval and early modern times communicated with each other in Latin, and, probably as a form of showing that they were members of this elite club, often converted their names to a Latin form. Thus, one </span>Aldo Pio Manuzio, a Venetian scholar and a very early book printer, took the name Aldus Pius Manutius. Francis Bacon published his "Novum Organum" (which was in Latin) as "Franciscus Baconis". </p><p>Things get doubly complex as people and their names move from one
culture to another. Many people of Chinese origin reverse the order of
their names from family name first then given name to the preferred
order in Western countries that places the family name last. In some cases, as with science fiction author Liu Cixin, a change for the Western marketplace creates a bit of confusion for anyone wanting to correctly encode this Chinese name.</p><a href="https://blogger.googleusercontent.com/img/a/AVvXsEhjJX1ER7PbjHMeekrZjru3I9rRCn1c0Ag3v3A31G9O9E8yKRTyPUJud7Ytpgc1JRUfueHbw743aqUeXWAp2Yem6_Ko1vi_NnfpsyDJKzqa_MA8ug6UH5m3uc-58lLP5rqsvs4n_qksEaF4WRGlrM4YzFRI78olRvDXEiL71n-Qes9CXQvcPEyXzPaFIg=s252" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="252" data-original-width="242" height="193" src="https://blogger.googleusercontent.com/img/a/AVvXsEhjJX1ER7PbjHMeekrZjru3I9rRCn1c0Ag3v3A31G9O9E8yKRTyPUJud7Ytpgc1JRUfueHbw743aqUeXWAp2Yem6_Ko1vi_NnfpsyDJKzqa_MA8ug6UH5m3uc-58lLP5rqsvs4n_qksEaF4WRGlrM4YzFRI78olRvDXEiL71n-Qes9CXQvcPEyXzPaFIg=w185-h193" width="185" /></a><a href="https://blogger.googleusercontent.com/img/a/AVvXsEgfbukYDys0go38Da-oKkzyjAliveqgCpCHBfgu6ZTpiz_oV0FeAUgrPZa6WCcFrTPTjnCEtmfYf6IANmMgyYpPEtjnjq7WDeR6pFB1QonsMD75mWvGZPpt9wbZyvRA_ncJkURQ86wvV7QJct6UY08L6lCU6JXTrC2tHvU_mqINQkmlSDneyCeiCzHfSA=s207" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="207" data-original-width="206" height="173" src="https://blogger.googleusercontent.com/img/a/AVvXsEgfbukYDys0go38Da-oKkzyjAliveqgCpCHBfgu6ZTpiz_oV0FeAUgrPZa6WCcFrTPTjnCEtmfYf6IANmMgyYpPEtjnjq7WDeR6pFB1QonsMD75mWvGZPpt9wbZyvRA_ncJkURQ86wvV7QJct6UY08L6lCU6JXTrC2tHvU_mqINQkmlSDneyCeiCzHfSA=w172-h173" width="172" /></a><br /><p></p><p>Note that his translator, Ken Liu, an American, uses the Western form of his own name. So this book cover is a good illustration of the name problem across cultures.<br /></p><h1 style="text-align: left;">Names in Metadata</h1><p style="text-align: left;"><span style="font-size: small;">How we handle names in metadata design depends mainly on the intended application functions for the data. I give below some key functions that use names, but this is an incomplete list. I can see these four as key purposes for names and their encoding in metadata:</span></p><p style="text-align: left;"><span style="font-size: small;">1. <b>Display</b> - Names get displayed in a number of different contexts, from phone books to faculty listings on a web site to conference name tags. Displays may use all or only part of a name, and there are a variety of ways that one can order the name parts.<br /></span></p><p style="text-align: left;"><span style="font-size: small;"> </span></p><p style="text-align: left;"><span style="font-size: small;">2. <b>Disambiguation</b> - Which Mary Jones is this? How do I identify and find the one that I am looking for?<br /></span></p><p style="text-align: left;"><span style="font-size: small;">3. <b>Addressing</b> - We do want to address people appropriately, and we also want to talk <i>about</i> them appropriately. <br /></span></p><p style="text-align: left;"><span style="font-size: small;">4. <b>Finding</b> - Searching via keyword is without context, so I'll assume that all name forms can be searched in that way. I will describe "finding" as meaning a search for a specific, known name.</span></p><p style="text-align: left;"><span style="font-size: small;">I'll trace these through some metadata schemas to illustrate the metadata capabilities one might have.<br /></span></p><h3 style="text-align: left;"><span style="font-size: small;">Library of Congress (and other libraries)</span></h3><p><span style="font-size: small;">Libraries have been dealing with names and name forms for, well, forever; as long as there have been libraries. The set of rules for determining what name to enter for someone in the library catalog is many, many tens of pages long, and there are separate rules for personal names, corporate names, and family names. Yet library name practices have their limitations, in particular that names are entered as strings that are to be used to create a specific alphabetical sort order that begins with the surname, followed by a comma, and then the forename(s). </span> <br /></p><p style="margin-left: 40px; text-align: left;">Dempsey, Martin, 1904- <br />Dempsey, Martin E. <br />Dempsey, Mary. <br />Dempsey, Mary A. <br /></p><p style="text-align: left;">Display by family name works well for Western names with family names, but not for Eastern names that place the family name first. <br /></p><p style="margin-left: 40px; text-align: left;"><span> </span>Mao, Zedong</p><p>Following Chinese name practice his name would naturally be given as "Mao Zedong" because the family name is always given first. If one attempts to use the comma to revert names to their natural order, say from "Smith, Jane" to "Jane Smith" then you would also end up with "Zedong Mao" which is not correct in that cultural context. A culturally sensitive "natural order" display is not supported by this metadata.<span style="font-size: small;"> </span></p><p style="text-align: left;"><span style="font-size: small;"><span style="font-size: small;">The primary display form is the Western one of lastname-comma-first names, but there are exceptions for entry by forename, which is given specific coding:</span></span> </p><p style="margin-left: 40px; text-align: left;">Arnaldur Indriðason, 1961-<br />Homer</p><span style="font-size: small;">As I've shown in the Mao Zedong example, the encoding of name parts in library data does not provide what you might need to create other display forms. In the case of </span><span style="font-size: small;">Arnaldur </span><span style="font-size: small;"><span style="font-size: small;">Indriðason, outside of the library need to alphabetize its entries, you may want to know that </span></span><span style="font-size: small;"> </span><span style="font-size: small;"><span style="font-size: small;">Indriðason is a patronymic if you intend to use the name to address the person as he would be addressed in his culture. The example of "Mao, Zedong" is lacking the information that this is a name in a culture that regularly refers to people with their surname preceding their given name (and without a comma). You would want to know that this should be rendered as "Mao Zedong" when used in that context. </span></span><p><span style="font-size: small;"><span style="font-size: small;">As you can see in the examples above, the Library of Congress name practice goes beyond just the name and adds elements that are meant to inform and clarify. It includes dates (birth, death); titles and other terms associated with a name (Pope, Jr., illustrator); enumeration (II); and fuller form of the name, which fills in portions of the name that use initials ("</span></span><span style="font-size: small;"><span style="font-size: small;">Boyle, Timothy D. (Timothy Dale)"). Interestingly, the "III" in Pope Pius III is an enumeration, while the "III" in "</span></span><span style="font-size: small;">John R </span>Kennedy,<b> </b>III" is an "other term associated with a name." I'm going to guess that this primarily relates to the positioning of the "III" in the display. This illustrates a tension between identifying parts of the name and providing the desired display of those parts.<br /></p><p><span style="font-size: small;"><span style="font-size: small;">There is a another problem with "title and other terms" because it is a catchall element that doesn't distinguish between some very different types of data. The documentation lists:</span></span></p><ul style="text-align: left;"><li>titles designating rank, office, or nobility, e.g., Sir</li><li><span style="font-size: small;"><span style="font-size: small;">terms of address, e.g., Mrs.</span></span><br /></li><li><span style="font-size: small;"><span style="font-size: small;">initials of an academic degree or denoting membership in an organization, e.g., F.L.A.</span></span><span style="font-size: small;"><span style="font-size: small;"> </span></span></li><li><span style="font-size: small;"><span style="font-size: small;">a roman numeral used with a surname</span></span></li><li><span style="font-size: small;"><span style="font-size: small;">other words or phrases associated with the name, e.g., clockmaker, Saint.</span></span></li></ul><span style="font-size: small;"><span style="font-size: small;"></span></span><p><span style="font-size: small;"><span style="font-size: small;">As you can see, some of these would display before the name in a "natural order" display:</span></span></p><ul style="text-align: left;"><li><span style="font-size: small;"><span style="font-size: small;"><i>Sir</i> Paul McCartney</span></span></li><li><span style="font-size: small;"><span style="font-size: small;"><i>Mrs.</i> Harriet Ward</span></span></li></ul><p><span style="font-size: small;"><span style="font-size: small;">While others display afterward:</span></span></p><ul style="text-align: left;"><li><span style="font-size: small;"><span style="font-size: small;">John Kennedy, <i>Jr</i>.</span></span></li><li><span style="font-size: small;"><span style="font-size: small;">John Kennedy, <i>III</i> <br /></span></span></li></ul><div><p><span style="font-size: small;"><span style="font-size: small;"> And some can be either or both:</span></span></p><ul style="text-align: left;"><li><span style="font-size: small;"><span style="font-size: small;"><i>Dr.</i> Paul Johnson, <i>DDS</i></span></span></li><li><span><i>Dr.</i> Sophie Jones, <i>Ph.D., F.I.P.A</i>.</span></li></ul><p><span style="font-size: small;"><span style="font-size: small;">There is always the need to disambiguate between people with the same name. Some of these "other terms" work well in identifying a person:</span></span></p><p style="margin-left: 40px; text-align: left;"><span style="font-size: small;"><span style="font-size: small;">Boyle, Tom <i>(Professor)</i></span></span></p><p style="margin-left: 40px; text-align: left;"><span style="font-size: small;"><span style="font-size: small;">Boyle, Tom <i>(Spiritualist)</i></span></span></p><p><span style="font-size: small;"><span style="font-size: small;">However, the clarification between identical names used most often in library name data is the dates of birth and death. These used to be included only when necessary to distinguish between identical names but the information is now included whenever it is available to the cataloger. This makes the dates an integral part of the name, much as the roman numerals of the names of Popes. </span></span></p><p style="margin-left: 40px; text-align: left;">Pius I, Pope, d. ca. 154 </p><p style="margin-left: 40px; text-align: left;">
Pius II, Pope, 1405-1464
</p><p><span style="font-size: small;"><span style="font-size: small;">Although perhaps once useful for the purpose of distinguishing otherwise identical names, the sheer number of people who are included in library catalogs has greatly limited the utility of these dates for disambiguation.</span></span></p><p style="margin-left: 40px; text-align: left;"><span style="font-size: small;"><span style="font-size: small;">Kennedy, John, 1919-1945<br />Kennedy, John, 1921-<br />Kennedy, John, 1926-1994<br />Kennedy, John, 1928-<br />Kennedy, John, 1931-<br />Kennedy, John, 1931-2004<br />Kennedy, John, 1934-2012<br />Kennedy, John, 1939-<br />Kennedy, John, 1940-<br />Kennedy, John, 1947-<br />Kennedy, John, 1948-<br />Kennedy, John, 1951-<br />Kennedy, John, 1953-<br />Kennedy, John, 1956-<br />Kennedy, John, 1959-<br />Kennedy, John, 1963-<br />Kennedy, John, 1965-<br />Kennedy, John, 1973-<br />Kennedy, John, -1988. <br /></span></span></p><p>There
is provision for alternate versions of names in library practice although these reside in a
separate file and are not always linked to the primary name in library
databases.</p><p style="margin-left: 40px; text-align: left;"><span style="font-size: small;"><span style="font-size: small;"><span style="font-size: small;"><span style="font-size: small;">Boyle, Thomas John<br /></span></span></span></span><span style="font-size: small;"><span style="font-size: small;"><span style="font-size: small;"><span style="font-size: small;"> see: Boyle, T. C. </span></span> <br /></span></span></p><p><span style="font-size: small;"><span style="font-size: small;">The library name practices, although probably the most detailed of any metadata name schemes, are not very generalizable; they serve one designated application, which is the alphabetical order of the entries in the library catalog. <br /></span></span></p><p></p><h3 style="text-align: left;">Dublin Core</h3><p><span style="font-size: small;"><span style="font-size: small;">Dublin Core is absolutely minimal when it comes to names, as "core" implies. It provides only one property, dct:creator, without further detail. It also does not distinguish between persons and organizations: both can be coded as "creator" with an implicit class of Agent. Any further intelligence must be provided elsewhere in a metadata scheme that makes use of Dublin Core. <br /></span></span></p><p><span style="font-size: small;"><span style="font-size: small;">Dublin Core does allow for the value of the dct:creator property to be either a literal or an IRI or Bnode, and the encoding of the value of the IRI could be a more precise name form. Using an IRI could also be a method for providing a unique identity for the creator. <br /></span></span></p><h3 style="text-align: left;">FOAF</h3><p><span style="font-size: small;"><span style="font-size: small;">The "Friend of a Friend" vocabulary is about people, their names, and some modern social connectivity: email address, web site, etc. FOAF has three name properties:</span></span></p><ul style="text-align: left;"><li><span style="font-size: small;"><span style="font-size: small;">foaf:name - which can be used to an entire name, undifferentiated in terms of types of name</span></span></li><li><span style="font-size: small;"><span style="font-size: small;">foaf:familyName<b> </b>&<b> </b>foaf:givenName - intended to be used together (but with no mechanism to enforce that) this allows an obvious separation between the names. How they would display is left to the applications that make use of them. </span></span></li></ul><p><span style="font-size: small;"><span style="font-size: small;">The </span></span><span style="font-size: small;"><span style="font-size: small;"><span style="font-size: small;"><span style="font-size: small;">foaf:familyName<b> </b>and<b> </b>foaf:givenName </span></span>cover a limited set of name forms. In the context of many online sites this may suffice, especially where there is no enforcement of "real" names. Given that FOAF was developed for use within and between online social sites, it avoids the need for historical forms of names.<br /></span></span></p><p><span style="font-size: small;"><span style="font-size: small;">All of these are defined as taking literal values, which we know does not provide an unambiguous identity for a person. There are properties defined in FOAF under the "Social Web" rubric, </span></span><span style="font-size: small;"><span style="font-size: small;"><span style="font-size: small;"><span style="font-size: small;">such as an email address,</span></span> that should serve to disambiguate persons in a particular social context. These are not, however, part of the name itself.</span></span></p><h3 style="text-align: left;">schema.org</h3><p><span style="font-size: small;"><span style="font-size: small;">The vocabulary <a href="http://schema.org">schema.org</a> was developed to provide "</span></span>structured data on the
Internet". (This is exactly the original impetus behind Dublin Core. How that went south, and what schema.org attempts to do instead, is beyond this post.) The vocabulary listed under the <a href="https://schema.org/Person">person schema</a> is extensive, although only a few elements are directly related to names:</p><p style="margin-left: 40px; text-align: left;">sdo:familyName, sdo:givenName, sdo:additionalName</p><p>sdo:givenName, is defined as the "first name" and sdo:familyName, is defined as the "last name". sdo:additionalName, is "An additional name for a Person, can be used for a middle name". This latter is highly flexible but at the same time non-specific. It also creates some confusion in terms of the order of names for anyone whose name does not fit the exact "first-middle-last" pattern. As shown above, it's not totally uncommon to have more than one name that can fit into any of those particular buckets. Presumably the properties are repeatable, but they are defined with the singular term "name". It also does not clarify a display order. </p><p style="margin-left: 40px; text-align: left;">sdo:givenName "T."<br />sdo:familyName "Boyle"<br />sdo:additionalName "C."<br /></p><p>Schema.org does have properties for both pre-name and post-name honorifics. The examples given for these are: sdo:honorificPrefix (Dr., Mrs.); sdo:honorificSuffix (M.D., PhD). These examples don't make it clear if it might be possible to encode:<br /></p><p>sdo:givenName "Charles"<br />sdo:honorificSuffix "Prince of Wales"</p><p>or</p><p>sdo:givenName "Pius"<br />sdo:honorificPrefix "Pope"<br />sdo:honorificSuffix "II"<br /></p><p>In any case it appears that this would not distinguish between the informal honorifics like "Esq." and those that are essential parts of the name such as titles of nobility. There also does not seem to be an obvious way to encode non-honorific suffixes, such as "Jr." or "III". </p><p>Without some strong guidance, it would be hard to know which of these properties would be used for the parts of a name like María de la
Purificación Zapatero Valero. We'll see a possible solution to this with Wikidata, below.<br /></p><h3 style="text-align: left;">Wikipedia</h3><p>Wikipedia has probably millions of articles for people and therefore has to deal with the question of names. Their search does not distinguish between names and other article topics, and all are searched in left-to-right natural order in a drop-down box. Names are article titles just as any topic can be an article title.<br /></p><p>There is no special coding of the name or parts of the name - it is simply a string of characters. Where more than one person has the same name article creators must add something to disambiguate the name which is usually done by adding an area of activity and perhaps a location associated with that activity:</p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/a/AVvXsEhWeXDsJvXGcGkj5ISskqbkFa4PR-MCmJUoOYaoCkbH2YwH_CuIItJLw39ezzlu3o8LsK_eCXDuPy3Y8N4daqsh55qqacc0KLGCgvHNMJ1IUubFFDN7_941jEMqXupwAx_NDTjjGqQUv_9vdLdrA8b46SKxKPU_FtpFjmVU5lTlztkYE9IKYVrOAAQ9-A=s466" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="404" data-original-width="466" height="173" src="https://blogger.googleusercontent.com/img/a/AVvXsEhWeXDsJvXGcGkj5ISskqbkFa4PR-MCmJUoOYaoCkbH2YwH_CuIItJLw39ezzlu3o8LsK_eCXDuPy3Y8N4daqsh55qqacc0KLGCgvHNMJ1IUubFFDN7_941jEMqXupwAx_NDTjjGqQUv_9vdLdrA8b46SKxKPU_FtpFjmVU5lTlztkYE9IKYVrOAAQ9-A=w200-h173" width="200" /></a></div><br /><p>Wikipedia also has a special type of page where topics that have common terms, including names, can be further defined.</p><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/a/AVvXsEhPz6tizXz-ZoEwJMdHtQLIzFStxAe9Xm066oYpQTgZFgj0FuTGL1m8pmlJZ4LrosXT79w4p9Bitcde-_kgZak72sSsyiCbz6dXaohZTOXZMF2s2tZy8MOEQyZ0404TIYjNzUc3id4l2mW9xHJUGwd8bhPKMHxOon96BlDSoHXUKkh8-1M7h35Jj0DJkw=s1178" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="592" data-original-width="1178" height="203" src="https://blogger.googleusercontent.com/img/a/AVvXsEhPz6tizXz-ZoEwJMdHtQLIzFStxAe9Xm066oYpQTgZFgj0FuTGL1m8pmlJZ4LrosXT79w4p9Bitcde-_kgZak72sSsyiCbz6dXaohZTOXZMF2s2tZy8MOEQyZ0404TIYjNzUc3id4l2mW9xHJUGwd8bhPKMHxOon96BlDSoHXUKkh8-1M7h35Jj0DJkw=w400-h203" width="400" /></a></div> </div><div>These pages allow an explanation to distinguish between people who share a name. It goes beyond the parenthetical phrases that are used to create unique article names for persons with the same name, and is much more human-friendly than the birth and death dates that library cataloging relies on. Yet while Wikipedia excels in disambiguation, its encoding for names is limited to a single property, "name", in the infobox for a person, although it also allows for honorifics and for alternative forms of the name. </div><div> </div><div><div style="margin-left: 40px; text-align: left;"><a href="https://blogger.googleusercontent.com/img/a/AVvXsEjgOVHeI3OC5eWx_Dp5ICyZ4F0vpOZQ1IKxqqHhx1TwCgR1wbHG_MLeUpy9Iwuy9Sflg4Pig_NrMnY9YoF0E4sW2TYzye1NyUNoX2hpjrQF8zH8O1AozOsmz10vAPkNEigsV5Nss3vuhUH97xF5fJ5qt_72aL3QLxdRTyivxFlI9Z2DvjIE6ihMSsg6hA=s454" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="428" data-original-width="454" height="189" src="https://blogger.googleusercontent.com/img/a/AVvXsEjgOVHeI3OC5eWx_Dp5ICyZ4F0vpOZQ1IKxqqHhx1TwCgR1wbHG_MLeUpy9Iwuy9Sflg4Pig_NrMnY9YoF0E4sW2TYzye1NyUNoX2hpjrQF8zH8O1AozOsmz10vAPkNEigsV5Nss3vuhUH97xF5fJ5qt_72aL3QLxdRTyivxFlI9Z2DvjIE6ihMSsg6hA=w200-h189" width="200" /></a></div><p style="text-align: left;">Because the various Wikipedias are divided by language, there are properties for translations and transliterations of names, and it allows for name changes over the course of a person's life. <br /></p><h2 style="text-align: left;">Wikidata</h2><p style="text-align: left;">Wikidata began by extracting data points from the Wikipedia entries, primarily from the infoboxes, but has grown beyond that to a database of facts that is edited directly. Perhaps because it is massively crowd-sourced, a <a href="https://www.wikidata.org/wiki/Wikidata:List_of_properties/name">long list of name properties</a> have been developed. In addition to the usual <i>given name</i> and <i>family name</i> there are terms like <i>demonym </i>(a name representing a place), <i>second family name in Spanish name, Roman cognomen </i>(ancient surname)<i>, patronym or matronym </i>(names representing the person's father or mother)<i>, first family name in Portuguese name, </i>and many others. </p><p style="text-align: left;">Also because it is crowd-sourced there should be no expectation that
this list is complete or balanced. It most likely represents a modicum
of self-interest on the part of participants.</p><h2 style="text-align: left;">Conclusion (?)<br /></h2><p>Any solution in this area needs to recognize that one size does not fit all. For some applications a single "name=[string]" will be sufficient and it would be seriously counter-productive to force those folks to engage in detailed encoding. Another barrier to detailed encoding is that few people have knowledge to encode the universe of name forms at a detailed level. Requiring metadata creators to make distinctions outside of their understanding would only result in error-ridden metadata. Better a blind single string than mis-coded details. Yet there will be applications and their metadata communities that can or must make use of the subtleties of name details that are not of interest to others.</p><p>Because of both the great variety of name forms and the variability of applications that make use of names, I recommend a metadata vocabulary that follows the principle of minimum semantic commitment. This means a vocabulary that includes broad classes and properties that can be used as is where detailed coding is not needed or desired, but which can be extended to accommodate many different contexts. </p><p>The trick then is to define broad classes that aid in defining semantics but do little restriction. Classes for things like "Agent", with subclasses for "Person", "Groups of Persons", and perhaps "Non-persons". Properties could begin with "name" which could be subdivided into any definable part of a name that people find useful. Further specificity can be provided by application profiles that define such requirements as cardinality or value types for the various properties. Applications themselves could contain rules for the displays that are needed for their use cases.<br /></p><p>The challenge now is to find a standards group that is interested to take this on.<br /></p><p>-------</p><p>* With perhaps a few exceptions. I once heard <a href="https://en.wikipedia.org/wiki/Lorcan_Dempsey">Lorcan Dempsey</a> opine that person's names would be much more useful if parents would just give their children unique names, "... like Lorcan Dempsey."</p><p><br /></p><p></p></div><br />Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com7tag:blogger.com,1999:blog-3338174527262061848.post-26503609596885409402021-08-12T14:38:00.001-07:002021-08-12T14:38:13.186-07:00Phil Agre and the gendered Internet<p>There is an article today in the <a href="Why does the space you "explore" in Gopher or Mosaic look empty even when it's full of other people? Why isn't there a mechanism for asking for help? " target="_blank">Washington Post</a> about the odd disappearance of a computer science professor named <a href="https://en.wikipedia.org/wiki/Philip_E._Agre" target="_blank">Phil Agre</a>. The article, entitled "<span data-qa="headline-text">He predicted the dark side of the Internet 30 years ago. Why did no one listen?" reminded me of a <a href="http://kcoyle.net/agre-october-1994.html" target="_blank">post by Agre in 1994</a> after a meeting of <a href="https://en.wikipedia.org/wiki/Computer_Professionals_for_Social_Responsibility" target="_blank">Computer Professionals for Social Responsibility</a>. Although it annoyed me at the time, a <a href="http://kcoyle.net/njw.html" target="_blank">talk that I gave there</a> triggered in him thoughts of gender issues; as a women I was very much in the minority at the meeting, but that was not the topic of my talk. But my talk also gave Agre thoughts about the missing humanity on the Web.</span></p><p><span data-qa="headline-text">I had a couple of primary concerns, perhaps not perfectly laid out, in my talk, "<a href="http://kcoyle.net/njw.html" target="_blank">Access, not Just Wires</a>." I was concerned about what was driving the development of the Internet and the lack of a service ethos regarding society. Access at the time was talked about in terms of routers, modems, T-1 lines. There was no thought to organizing or preserving of online information. There was no concept of "equal access". There was no thought to how we would democratize the Web such that you didn't need a degree in computer science to find what you needed. <br /></span></p><p><span data-qa="headline-text">I was also very concerned about the commercialization of information. I was frustrated watching the hype as information was touted as <b>the</b> product of the information age. (This was before we learned that "you are the <b>product</b>, not the user" in this environment.) Seen from the tattered clothes and barefoot world of libraries, the money thrown at the jumble of un-curated and unorganized "information" on the web was heartbreaking. I said:<br /></span></p><blockquote>
<p> "It's clear to me that the information highway isn't much about information.
It's about trying to find a new basis for our economy. I'm pretty sure I'm not
going to like the way information is treated in that economy. We know what kind
of information sells, and what doesn't. So I see our future as being a mix of
highly expensive economic reports and cheap online versions of the National
Inquirer. Not a pretty picture." - kcoyle in <i>Access, not Just Wires</i><br /></p></blockquote><p></p><p><span data-qa="headline-text"></span></p><p><span data-qa="headline-text"> Little did I know how bad it would get.</span></p><p><span data-qa="headline-text">Like many or most people, Agre heard "libraries" and thought "female." But at least this caused him to think, earlier than many, about how our metaphors for the Internet were inherently gendered. </span></p><blockquote><span data-qa="headline-text">"</span>Discussing her speech with another CPSR activist ... later that evening, I suddenly connected several things that had been bothering me about the language and practice of the Internet. The result was a partial answer to the difficult question, in what sense is the net "gendered"?" - Agre, TNO, October 1994</blockquote><p>This led Agre to think about how we spoke then about the Internet, which was mainly as an activity of "exploring." That metaphor is still alive with Microsoft's Internet Explorer, but was also the message behind the main Web browser software of the time, <a href="https://en.wikipedia.org/wiki/Netscape_Navigator" target="_blank">Netscape Navigator</a>. He suddenly saw how "explore" was a highly gendered activity:</p><p></p><blockquote>"Yet for many people, "exploring" is close to defining the experience of the net. It is clearly a gendered metaphor: it has historically been a male activity, and it comes down to us saturated with a long list of meanings related to things like colonial expansion, experiences of otherness, and scientific discovery. Explorers often die, and often fail, and the ones that do neither are heroes and role models. This whole complex of meanings and feelings and strivings is going to appeal to those who have been acculturated into a particular male-marked system of meanings, and it is not going to offer a great deal of meaning to anyone who has not. The use of prestigious artifacts like computers is inevitably tied up with the construction of personal identity, and "exploration" tools offer a great deal more traction in this process to historically male cultural norms than to female ones." - Agre, TNO, October 1994<br /></blockquote>He decried the lack of social relationships on the Internet, saying that although you know that other people are there, you cannot see them. <p></p><blockquote><p>"Why does the space you "explore" in Gopher or Mosaic look empty even when it's full of other people?" - Agre, TNO, October 1994</p></blockquote><p></p><p></p><p> </p><p>None of us knew at the time that in the future some people would experience the Internet entirely and exclusively as full of other people in the forms of Facebook, Twitter and all of the other sites that grew out of the embryos of <a href="https://en.wikipedia.org/wiki/Bulletin_board_system">bulletin board systems</a>, the <a href="https://en.wikipedia.org/wiki/The_WELL" target="_blank">Well</a>, and <a href="https://en.wikipedia.org/wiki/AOL">AOL</a>. We feared that the future Internet would not have the even-handedness of libraries, but never anticipated that Russian bots and Qanon promoters would reign over what had once been a network for the exchange of scientific information. <br /></p><p>It hurts now to read through Agre's post arguing for a more library-like online information system because it is pretty clear that we blew through that possibility even before the 1994 meeting and were already taking the first steps toward to where we are today.<br /></p><p>Agre walked away from his position at UCLA in 2009 and has not resurfaced, although there have been reports at times (albeit not recently) that he is okay. Looking back, it should not surprise us that someone with so much hope for an online civil society should have become discouraged enough to leave it behind. Agre was hoping for reference services and an Internet populated with users with:</p><blockquote><p>"...the skills of composing clear texts, reading with an awareness of different possible interpretations, recognizing and resolving conflicts, asking for help without feeling powerless, organizing people to get things done, and embracing the diversity of the backgrounds and experiences of others." - Agre, TNO, October 1994<br /></p></blockquote><p> Oh, what world that would be!</p><p></p><p><span data-qa="headline-text"></span></p>Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com2tag:blogger.com,1999:blog-3338174527262061848.post-73506918412517482402021-03-01T11:54:00.003-08:002021-06-19T12:58:18.336-07:00Digitization Wars, Redux<p><i> (NB: IANAL) </i></p><p><i> Because this is long, you can download it as a PDF <a href="http://kcoyle.net/DigitizationWars.pdf">here</a>.</i><br /></p><p>From 2004 to 2016 the book world (authors, publishers, libraries, and booksellers) was involved in the complex and legally fraught activities around Google’s book digitization project. Once known as “Google Book Search,” the company claimed that it was digitizing books to be able to provide search services across the print corpus, much as it provides search capabilities over texts and other media that are hosted throughout the Internet. <br /></p><p>Both the US Authors Guild and the Association of American Publishers sued Google (both separately and together) for violation of copyright. These suits took a number of turns including proposals for settlements that were arcane in their complexity and that ultimately failed. Finally, in 2016 the legal question was decided: digitizing to create an index is fair use as long as only minor portions of the original text are shown to users in the form of context-specific snippets. </p><p>We now have another question about book digitization: can books be digitized for the purpose of substituting remote lending in the place of the lending of a physical copy? This has been referred to as “Controlled Digital Lending (CDL),” a term developed by the Internet Archive for its online book lending services. The Archive has considerable experience with both digitization and providing online access to materials in various formats, and its Open Library site has been providing digital downloads of out of copyright books for more than a decade. Controlled digital lending applies solely to works that are presumed to be in copyright. </p><p>Controlled digital lending works like this: the Archive obtains and retains a physical copy of a book. The book is digitized and added to the Open Library catalog of works. Users can borrow the book for a limited time (2 weeks) after which the book “returns” to the Open Library. While the book is checked out to a user no other user can borrow that “copy.” The digital copy is linked one-to-one with a physical copy, so if more than one copy of the physical book is owned then there is one digital loan available for each physical copy. </p><p>The Archive is not alone in experimenting with lending of digitized copies: some libraries have partnered with the Archive’s digitization and lending service to provide digital lending for library-owned materials. In the case of the Archive the physical books are not available for lending. Physical libraries that are experimenting with CDL face the added step of making sure that the physical book is removed from circulation while the digitized book is on loan, and reversing that on return of the digital book. </p><p>Although CDL has an air of legality due to limiting lending to one user at a time, authors and publishers associations had raised objections to the practice. [nwu] However, in March of 2020 the Archive took a daring step that pushed their version of the CDL into litigation: using the closing of many physical libraries due to the COVID pandemic as its rationale, the Archive renamed its lending service the National Emergency Library [nel] and eliminated the one-to-one link between physical and digital copies. Ironically this meant that the Archive was then actually doing what the book industry had accused it of (either out of misunderstanding or as an exaggeration of the threat posed): it was making and lending digital copies beyond its physical holdings. The Archive stated that the National Emergency Library would last only until June of 2020, presumably because by then the COVID danger would have passed and libraries would have re-opened. In June the Archive’s book lending service returned to the one-to-one model. Also in June a suit was filed by four publishers (Hachette, HarperCollins, Penguin Random House, and Wiley) in the US District Court of the Southern District of New York. [suit] </p><p>The Controlled Digital Lending, like the Google Books project, holds many interesting questions about the nature of “digital vs physical,” not only in a legal sense but in a sense of what it means to read and to be a reader today. The lawsuit not only does not further our understanding of this fascinating question; it sinks immediately into hyperbole, fear-mongering, and either mis-information or mis-direction. That is, admittedly, the nature of a lawsuit. What follows here is not that analysis but gives a few of the questions that are foremost in my mind.</p><h2 style="text-align: left;"> Apples and Oranges </h2><p> Each of the players in this drama has admirable reasons for their actions. The publishers explain in their suit that they are acting in support of authors, in particular to protect the income of authors so that they may continue to write. The Authors’ Guild provides some data on author income, and by their estimate the average full-time author earns less than $20,000 per year, putting them at poverty level.[aghard] (If that average includes the earnings of highly paid best selling authors, then the actual earnings of many authors is quite a bit less than that.) </p><p>The Internet Archive is motivated to provide democratic access to the content of books to anyone who needs or wants it. Even before the pandemic caused many libraries to close the collection housed at the Archive contained some works that are available only in a few research libraries. This is because many of the books were digitized during the Google Books project which digitized books from a small number of very large research libraries whose collections differ significantly from those of the public libraries available to most citizens. </p><p>Where the pronouncements of both parties fail is in making a false equivalence between some authors and all authors, and between some books and all books, and the result is that this is a lawsuit pitting apples against oranges. We saw in the lawsuits against Google that some academic authors, who may gain status based on their publications but very little if any income, did not see themselves as among those harmed by the book digitization project. Notably the authors in this current suit, as listed in the bibliography of pirated books in the appendix to the lawsuit, are ones whose works would be characterized best as “popular” and “commercial,” not academic: James Patterson, J. D. Salinger, Malcolm Gladwell, Toni Morrison, Laura Ingalls Wilder, and others. Not only do the living authors here earn above the poverty level, all of them provide significant revenue for the publishers themselves. And all of the books listed are in print and available in the marketplace. No mention is made of out-of-print books, no academic publishers seem to be involved. </p><p>On the part of the Archive, they state that their digitized books fill an educational purpose, and that their collection includes books that are not available in digital format from publishers:
</p><blockquote>“ While Overdrive, Hoopla, and other streaming services provide patrons access to latest best sellers and popular titles, the long tail of reading and research materials available deep within a library’s print collection are often not available through these large commercial services. What this means is that when libraries face closures in times of crisis, patrons are left with access to only a fraction of the materials that the library holds in its collection.”[cdl-blog]</blockquote><p>
This is undoubtedly true for some of the digitized books, but the main thesis of the lawsuit points out that the Archive has digitized and is also lending current popular titles. The list of books included in the appendix of the lawsuit shows that there are in-copyright and most likely in-print books of a popular reading nature that have been part of the CDL. These titles are available in print and may also be available as ebooks from the publishers. Thus while the publishers are arguing that current, popular books should not be digitized and loaned (apples), the Archive is arguing that they are providing access to items not available elsewhere, and for educational purposes (oranges). </p><h2 style="text-align: left;">The Law </h2><p>The suit states that publishers are not questioning copyright law, only violations of the law.
</p><blockquote>“For the avoidance of doubt, this lawsuit is not about the occasional transmission of a title under appropriately limited circumstances, nor about anything permissioned or in the public domain. On the contrary, it is about IA’s purposeful collection of truckloads of in-copyright books to scan, reproduce, and then distribute digital bootleg versions online.” ([Suit] Page 3).</blockquote><p>
This brings up a whole range of legal issues in regard to distributing digital copies of copyrighted works. There have been lengthy arguments about whether copyright law could permit first sale rights for digital items, and the answer has generally been no; some copyright holders have made the argument that since transfer of a digital file is necessarily the making of a copy there can be no first sale rights for those files. [1stSale] [ag1] Some ebook systems, such as the Kindle, have allowed time-limited person-to-person lending for some ebooks. This is governed by license terms between Amazon and the publishers, not by the first sale rights of the analog world. </p><p>Section 108 of the copyright law does allow libraries and archives to make a limited number of copies The first point of section 108 states that libraries can make a single copy of a work as long as 1) it is not for commercial advantage, 2) the collection is open to the public and 3) the reproduction includes the copyright notice from the original. This sounds to be what the Archive is doing. However, the next two sections (b and c) provide limitations on that first section that appear to put the Archive in legal jeopardy: section “b” clarifies that copies may be made for preservation or security; section “c” states that the copies can be made if the original item is deteriorating and a replacement can no longer be purchased. Neither of these applies to the Archive’s lending. </p><p> In addition to its lending program, the Archive provides downloads of scanned books in DAISY format for those who are certified as visually impaired by the National Library Service for the Blind and Physically Handicapped in the US. This is covered in 121A of the copyright law, Title17, which allows the distribution of copyrighted works in accessible formats. This service could possibly be cited as a justification of the scanning of in-copyright works at the Archive, although without mitigating the complaints about lending those copies to others. This is a laudable service of the Archive if scans are usable by the visually impaired, but the DAISY-compatible files are based on the OCR’d text, which can be quite dirty. Without data on downloads under this program it is hard to know the extent to which this program benefits visually impaired readers. </p><h2 style="text-align: left;"> Lending </h2><p>Most likely as part of the strategy of the lawsuit, very little mention is made of “lending.” Instead the suit uses terms like “download” and “distribution” which imply that the user of the Archive’s service is given a permanent copy of the book
</p><blockquote>“With just a few clicks, any Internet-connected user can download complete digital copies of in-copyright books from Defendant.” ([suit] Page 2).
“... distributing the resulting illegal bootleg copies for free over the Internet to individuals worldwide.” ([suit] Page 14).</blockquote>
Publishers were reluctant to allow the creation of ebooks for many years until they saw that DRM would protect the digital copies. It then was another couple of years before they could feel confident about lending - and by lending I mean lending by libraries. It appears that Overdrive, the main library lending platform for ebooks, worked closely with publishers to gain their trust. The lawsuit questions whether the lending technology created by the Archive can be trusted.
<blockquote>“...Plaintiffs have legitimate fears regarding the security of their works both as stored by IA on its servers” ([suit] Page 47).</blockquote><p>
In essence, the suit accuses IA of a lack of transparency about its lending operation. Of course, any collaboration between IA and publishers around the technology is not possible because the two are entirely at odds and the publishers would reasonably not cooperate with folks they see as engaged in piracy of their property. </p><p>Even if the Archive’s lending technology were proven to be secure, lending alone is not the issue: the Archive copied the publishers’ books without permission prior to lending. In other words, they were lending content that they neither owned (in digital form) nor had licensed for digital distribution. Libraries pay, and pay dearly, for the ebook lending service that they provide to their users. The restrictions on ebooks may seem to be a money-grab on the part of publishers, but from their point of view it is a revenue stream that CDL threatens. </p><h2 style="text-align: left;">Is it About the Money? <br /></h2><blockquote>“... IA rakes in money from its infringing services…” ([suit] Page 40). (Note: publishers earn, IA “rakes in”)</blockquote>
<blockquote>“Moreover, while Defendant promotes its non-profit status, it is in fact a highly commercial enterprise with millions of dollars of annual revenues, including financial schemes that provide funding for IA’s infringing activities. ([suit] Page 4).</blockquote><p>
These arguments directly address section (a)(1) of Title 17, section 108: “(1) the reproduction or distribution is made without any purpose of direct or indirect commercial advantage”. </p><p>At various points in the suit there are references to the Archive’s income, both for its scanning services and donations, as well as an unveiled show of envy at the over $100 million that Brewster Kahle and his wife have in their jointly owned foundation. This is an attempt to show that the Archive derives “direct or indirect commercial advantage” from CDL. Non-profit organizations do indeed have income, otherwise they could not function, and “non-profit” does not mean a lack of a revenue stream, it means returning revenue to the organization instead of taking it as profit. The argument relating to income is weakened by the fact that the Archive is not charging for the books it lends. However, much depends on how the courts will interpret “indirect commercial advantage.” The suit argues that the Archive benefits generally from the scanned books because this enhances the Archive’s reputation which possibly results in more donations. There is a section in the suit relating to the “sponsor a book” program where someone can donate a specific amount to the Archive to digitize a book. How many of us have not gotten a solicitation from a non-profit that makes statements like: “$10 will feed a child for a day; $100 will buy seed for a farmer, etc.”? The attempt to correlate free use of materials with income may be hard to prove. </p><h2 style="text-align: left;">Reading </h2><p>Decades ago, when the service Questia was just being launched (Questia ceased operation December 21, 2020), Questia sales people assured a group of us that their books were for “research, not reading.” Google used a similar argument to support its scanning operation, something like “search, not reading.” The court decision in Google’s case decided that Google’s scanning was fair use (and transformative) because the books were not available for reading, as Google was not presenting the full text of the book to its audience.[suit-g] </p><p>The Archive has taken the opposite approach, a “books are for reading” view. Beginning with public domain books, many from the Google books project, and then with in-copyright books, the Archive has promoted reading. It developed its own in-browser reading software to facilitate reading of the books online. [reader] (*See note below)<br /></p><p>Although the publishers sued Google for its scanning, they lost due to the “search, not reading” aspect of that project. The Archive has been very clear about its support of reading, which takes the Google justification off the table. </p><p></p><blockquote>“Moreover, IA’s massive book digitization business has no new purpose that is fundamentally different than that of the Publishers: both distribute entire books for reading.” ([suit] Page 5). </blockquote><p></p><p> However, the Archive's statistics on loaned books shows that a large proportion of the books are used for 30 minutes or less. </p><p></p><blockquote>“Patrons may be using the checked-out book for fact checking or research, but we suspect a large number of people are browsing the book in a way similar to browsing library shelves.” [ia1] </blockquote><p></p><p> In its article on the CDL, the Center for Democracy and Technology notes that “the majority of books borrowed through NEL were used for less than 30 minutes, suggesting that CDL’s primary use is for fact-checking and research, a purpose that courts deem favorable in a finding of fair use.” [cdt]
The complication is that the same service seems to be used both for reading of entire books and as a place to browse or to check individual facts (the facts themselves cannot be copyrighted). These may involve different sets of books, once again making it difficult to characterize the entire set of digitized books under a single legal claim. </p><p>The publishers claim that the Archive is competing with them using pirated versions of their own products. That leads us to the question of whether the Archive’s books, presented for reading, are effectively substitutes for those of the publishers. Although the Archive offers actual copies, those copies that are significantly inferior to the original. However, the question of quality did not change the judgment in the lawsuit against copying of texts by Kinko’s [kinkos], which produced mediocre photocopies from printed and bound publications. It seems unlikely that the quality differential will serve to absolve the Archive from copyright infringement even though the poor quality of some of the books interferes with their readability. </p><h2 style="text-align: left;">Digital is Different <br /></h2><p>Publishers have found a way to monetize digital versions, in spite of some risks, by taking advantage of the ability to control digital files with technology and by licensing, not selling, those files to individuals and to libraries. It’s a “new product” that gets around First Sale because, as it is argued, every transfer of a digital file makes a copy, and it is the making of copies that is covered by copyright law. [1stSale] </p><p>The upshot of this is that because a digital resource is licensed, not sold, the right to pass along, lend, or re-sell a copy (as per Title 17 section 109) does not apply even though technology solutions that would delete the sender’s copy as the file safely reaches the recipient are not only plausible but have been developed. [resale] </p><p></p><blockquote>“Like other copyright sectors that license education technology or entertainment software, publishers either license ebooks to consumers or sell them pursuant to special agreements or terms.” ([suit] Page 15) </blockquote><p></p><blockquote>“When an ebook customer obtains access to the title in a digital format,
there are set terms that determine what the user can or cannot do with
the underlying file.”([suit] Page 16)</blockquote> <p></p><p></p><p>This control goes beyond the copyright holder’s rights in law: DRM can exercise controls over the actual use of a file, limiting it to specific formats or devices, allowing or not allowing text-to-speech capabilities, even limiting copying to the clipboard. </p><p></p><h2 style="text-align: left;">Publishers and Libraries </h2><p>The suit claims that publishers and libraries have reached an agreement, an equilibrium.
</p><blockquote> “To Plaintiffs, libraries are not just customers but allies in a shared mission to make books available to those who have a desire to read, including, especially, those who lack the financial means to purchase their own copies.” ([suit] Page 17).</blockquote>
In the suit, publishers contrast the Archive’s operation with the relationship that publishers have with libraries. In contrast with the Archive’s lending program, libraries are the “good guys.”
<blockquote>“... the Publishers have established independent and distinct distribution models for ebooks, including a market for lending ebooks through libraries, which are governed by different terms and expectations than print books.”([suit] Page 6).</blockquote>
These “different terms” include charging much higher prices to libraries for ebooks, limiting the number of times an ebook can be loaned. [pricing1] [pricing2]
<blockquote>“Legitimate libraries, on the other hand, license ebooks from publishers for limited periods of time or a limited number of loans; or at much higher prices than the ebooks available for individual purchase.” [agol]</blockquote>
The equilibrium of which publishers speak looks less equal from the library side of the equation: library literature is replete with stories about the avarice of publishers in relation to library lending of ebooks. Some authors/publishers even speak out against library lending of ebooks, claiming that this cuts into sales. (This same argument has been made for physical books.)
<blockquote>“If, as Macmillan has determined, 45% of ebook reads are occurring through libraries and that percentage is only growing, it means that we are training readers to read ebooks for free through libraries instead of buying them. With author earnings down to new lows, we cannot tolerate ever-decreasing book sales that result in even lower author earnings.” [agliblend][ag42]</blockquote><p>
The ease of access to digital books has become a boon for book sales, and ebook sales are now rising while hard copy sales fall. This economic factor is a motivator for any of those engaged with the book market. The Archive’s CDL is a direct affront to the revenue stream that publishers have carved out for specific digital products. There are indications that the ease of borrowing of ebooks - not even needing to go to the physical library to borrow a book - is seen as a threat by publishers. This has already played out in other media, from music to movies. </p><p>It would be hard to argue that access to the Archive’s digitized books is merely a substitute for library access. Many people do not have actual physical library access to the books that the Archive lends, especially those digitized from the collections of academic libraries. This is particularly true when you consider that the Archive’s materials are available to anyone in the world with access to the Internet. If you don’t have an economic interest in book sales, and especially if you are an educator or researcher, this expanded access could feel long overdue. </p><h2 style="text-align: left;">We need numbers </h2><p>We really do not know much about the uses of the Archive’s book collection. The lawsuit cites some statistics of “views” to show that the infringement has taken place, but the page in question does not explain what is meant by a “view”. Archive pages for downloadable files of metadata records also report “views” which most likely reflect views of that web page, since there is nothing viewable other than the page itself. Open Library book pages give “currently reading” and “have read” stats, but these are tags that users can manually add to the page for the work. To compound things, the 127 books cited in the suit have been removed from the lending service (and are identified in the Archive as being in the collection “<a href="https://archive.org/details/litigationworks">litigation works</a>) </p><p>Although numbers may not affect the legality of the controlled digital lending, the social impact of the Archive’s contribution to reading and research would be clearer if we had this information. Although the Archive has provided a small number of testimonials, a proof of use in educational settings would bolster the claims of social benefit which in turn could strengthen a fair use defense. </p><h3 style="text-align: left;">Notes</h3><p>(*) The NWU has a slide show [nwu2] that explains what it calls Controlled Digital Lending at the Archive. Unfortunately this document conflates the Archive's book Reader with CDL and therefore muddies the water. It muddies it because it does not distinguish between sending files to dedicated devices (which is what Kindle is) or dedicated software like what libraries use via software like Libby, and the Archive's use of a web-based reader. It is not beyond reason to suppose that the Archive's Reader software does not fully secure loaned items. The NWU claims that files are left in the browser cache that represent all book pages viewed: "There’s no attempt whatsoever to restrict how long any user retains these images". (I cannot reproduce this. In my minor experiments those files disappear at the end of the lending period, but this requires more concerted study.) However, this is not a fault of CDL but a fault of the Reader software. The reader is software that works within a browser window. In general, electronic files that require secure and limited use are not used within browsers, which are general purpose programs. </p><p>Conflating the Archive's Reader software with Controlled Digital Lending will only hinder understanding. Already CDL has multiple components:</p><ol style="text-align: left;"><li>Digitization of in-copyright materials</li><li>Lending of digital copies of in-copyright materials that are owned by the library in a 1-to-1 relation to physical copies<br /></li></ol><p>We can add #3, the leakage of page copies via the browser cache, but I maintain that poorly functioning software does not automatically moot points 1 and 2. I would prefer that we take each point on its own in order to get a clear idea of the issues.<br /></p><p>The NWU slides also refer to the Archive's API which allows linking to
individual pages within books. This is an interesting legal area because
it may be determined to be fair use regardless of the legality of the
underlying copy. This becomes yet another issue to be discussed by the
legal teams, but it is separate from the question of controlled digital lending. Let's stay focused.<br /></p><p>The International Federation of Library Associations has issued its own statement on Controlled Digital Lending at <a href="https://www.ifla.org/publications/node/93954">https://www.ifla.org/publications/node/93954</a><br /></p><h3 style="text-align: left;">Citations <br /></h3><p>[1stSale] <a href="https://abovethelaw.com/2017/11/a-digital-take-on-the-first-sale-doctrine/"> https://abovethelaw.com/2017/11/a-digital-take-on-the-first-sale-doctrine/</a> </p><p>[ag1]<a href="https://www.authorsguild.org/industry-advocacy/reselling-a-digital-file-infringes-copyright/">https://www.authorsguild.org/industry-advocacy/reselling-a-digital-file-infringes-copyright/</a> </p><p>[ag42] <a href="https://www.authorsguild.org/industry-advocacy/authors-guild-survey-shows-drastic-42-percent-decline-in-authors-earnings-in-last-decade/">https://www.authorsguild.org/industry-advocacy/authors-guild-survey-shows-drastic-42-percent-decline-in-authors-earnings-in-last-decade/</a> </p><p>[aghard] <a href="https://www.authorsguild.org/the-writing-life/why-is-it-so-goddamned-hard-to-make-a-living-as-a-writer-today/">https://www.authorsguild.org/the-writing-life/why-is-it-so-goddamned-hard-to-make-a-living-as-a-writer-today/</a></p>
<p><a href="https://www.authorsguild.org/industry-advocacy/macmillan-announces-new-library-lending-terms-for-ebooks/"><span style="color: black;">[aglibend]</span> https://www.authorsguild.org/industry-advocacy/macmillan-announces-new-library-lending-terms-for-ebooks/</a></p><p>
[agol] <a href="https://www.authorsguild.org/industry-advocacy/update-open-library/">https://www.authorsguild.org/industry-advocacy/update-open-library/</a> </p><p>[cdl-blog] <a href="https://blog.archive.org/2020/03/09/controlled-digital-lending-and-open-libraries-helping-libraries-and-readers-in-times-of-crisis">https://blog.archive.org/2020/03/09/controlled-digital-lending-and-open-libraries-helping-libraries-and-readers-in-times-of-crisis</a>/ </p><p>[cdt]
<a href="https://cdt.org/insights/up-next-controlled-digital-lendings-first-legal-battle-as-publishers-take-on-the-internet-archive/">https://cdt.org/insights/up-next-controlled-digital-lendings-first-legal-battle-as-publishers-take-on-the-internet-archive/</a> </p><p>[kinkos] <a href="https://law.justia.com/cases/federal/district-courts/FSupp/758/1522/1809457/">https://law.justia.com/cases/federal/district-courts/FSupp/758/1522/1809457</a></p><p>[nel] <a href="http://blog.archive.org/national-emergency-library/ ">http://blog.archive.org/national-emergency-library/ </a></p><p>[nwu]
<a href="https://nwu.org/book-division/cdl/appeal/">"Appeal from the victims of Controlled Digital Lending (CDL)"</a>. (Retrieved 2021-01-10) </p><div style="text-align: left;">[nwu2] <span style="font-family: times;"><span style="font-size: small;"><span style="left: 97.6724px; top: 123.513px; transform: scaleX(1.00356);">"What is the Internet Archive doing </span><span style="left: 354.57px; top: 201.314px; transform: scaleX(1.00218);">with our books?" <a href="https://nwu.org/wp-content/uploads/2020/04/NWU-Internet-Archive-webinar-27APR2020.pdf">https://nwu.org/wp-content/uploads/2020/04/NWU-Internet-Archive-webinar-27APR2020.pdf</a></span></span></span> </div><p>[pricing1] <a href="https://www.authorsguild.org/industry-advocacy/e-book-library-pricing-the-game-changes-again/"> https://www.authorsguild.org/industry-advocacy/e-book-library-pricing-the-game-changes-again/</a> </p><p>[pricing2] <a href="https://americanlibrariesmagazine.org/blogs/e-content/ebook-pricing-wars-publishers-perspective/">https://americanlibrariesmagazine.org/blogs/e-content/ebook-pricing-wars-publishers-perspective/</a> </p><p>[reader] <a href="https://openlibrary.org/dev/docs/bookreader">Bookreader</a> </p><p>[resale] <a href="https://www.hollywoodreporter.com/thr-esq/appeals-court-weighs-resale-digital-files-1168577">https://www.hollywoodreporter.com/thr-esq/appeals-court-weighs-resale-digital-files-1168577</a> </p><p>[suit] <a href="https://www.courtlistener.com/recap/gov.uscourts.nysd.537900/gov.uscourts.nysd.537900.1.0.pdf">https://www.courtlistener.com/recap/gov.uscourts.nysd.537900/gov.uscourts.nysd.537900.1.0.pdf</a> </p><p>[suit-g] <a href="https://cases.justia.com/federal/appellate-courts/ca2/13-4829/13-4829-2015-10-16.pdf?ts=1445005805"> https://cases.justia.com/federal/appellate-courts/ca2/13-4829/13-4829-2015-10-16.pdf?ts=1445005805</a></p>Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com0tag:blogger.com,1999:blog-3338174527262061848.post-69414889655410775612020-06-25T09:47:00.000-07:002020-06-25T09:47:13.407-07:00Women designing<br />
Those of us in the library community are generally aware of our premier "designing woman," the so-called "Mother of MARC," <a href="https://en.wikipedia.org/wiki/Henriette_Avram" target="_blank">Henriette Avram</a>. Avram designed the MAchine Reading Cataloging record in the mid-1960's, a record format that is still being used today. MARC was way ahead of its time using variable length data fields and a unique character set that was sufficient for most European languages, all thanks to Avram's vision and skill. I'd like to introduce you here to some of the designing women of the University of California library automation project, the project that created one of the first online catalogs in the beginning of the 1980's, <a href="https://en.wikipedia.org/wiki/Melvyl" target="_blank">MELVYL</a>. Briefly, MELVYL was a union catalog that combined data from the libraries of the nine (at that time) University of California campuses. It was first brought up as a test system in 1980 and went "live" to the campuses in <a href="http://kcoyle.blogspot.com/2020/05/1982.html" target="_blank">1982</a>.<br />
<br />
Work on the catalog began in or around 1980, and various designs were put forward and tested. Key designers were Linda Gallaher-Brown, who had one of the first masters degrees in computer science from UCLA, and Kathy Klemperer, who like many of us was a librarian turned systems designer.<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
</div>
<div class="separator" style="clear: both; text-align: center;">
</div>
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjRgoDGe0NypTioeQmpnRM12J6fp6_fgrneh1e_mItwibn1Pvb8izKS7Z4oPSbihjgqSE0vMxcip2CiEmvklGRRTaM5XA-dRHjawlFYEAKztUoruqAPSgtkla3BHnoO8JU4erMsUG2-iB6W/s1600/lbgkek.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="1200" data-original-width="1600" height="240" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjRgoDGe0NypTioeQmpnRM12J6fp6_fgrneh1e_mItwibn1Pvb8izKS7Z4oPSbihjgqSE0vMxcip2CiEmvklGRRTaM5XA-dRHjawlFYEAKztUoruqAPSgtkla3BHnoO8JU4erMsUG2-iB6W/s320/lbgkek.jpg" width="320" /></a></div>
We were struggling with how to create a functional relational database of bibliographic data (as defined by the MARC record) with computing resources that today would seem laughable but were "cutting edge" for that time. I remember Linda remarking that during one of her school terms she returned to her studies to learn that the newer generation of computers would have this thing called an "operating system" and she thought "why would you need one?" By the time of this photo she had come to appreciate what an operating system could do for you. The one we used at the time was IBM's OS 360/370.<br />
<br />
Kathy Klemperer was the creator of the database design diagrams that were so distinctive we called them "Klemperer-grams." Here's one from 1985:<br />
<table align="center" cellpadding="0" cellspacing="0" class="tr-caption-container" style="margin-left: auto; margin-right: auto; text-align: center;"><tbody>
<tr><td style="text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhjK5kH4QkT4tITsZIGuhzruslq6_I9lolZHAsYgXUwgEk84b1p-wgHrgGfLsl0xiLqm4Be8XuIcWqGJVeYegOE5U013df4bEguQp_Nh8JOjsPyxCwzTAQvG4aiswYEMnriblZA7Utt9exv/s1600/melvylDesign.jpg" imageanchor="1" style="margin-left: auto; margin-right: auto;"><img border="0" data-original-height="1237" data-original-width="1600" height="247" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhjK5kH4QkT4tITsZIGuhzruslq6_I9lolZHAsYgXUwgEk84b1p-wgHrgGfLsl0xiLqm4Be8XuIcWqGJVeYegOE5U013df4bEguQp_Nh8JOjsPyxCwzTAQvG4aiswYEMnriblZA7Utt9exv/s320/melvylDesign.jpg" width="320" /></a></td></tr>
<tr><td class="tr-caption" style="text-align: center;">MELVYL database design Klemperer-gram, 1985</td></tr>
</tbody></table>
Drawn and lettered by hand, not only did these describe a workable database design, they were impressively beautiful. Note that this not only predates the proposed 2009 RDA "database scenario" for a relational bibliographic design by 24 years, it provides a more detailed and most likely a more accurate such design.<br />
<table align="center" cellpadding="0" cellspacing="0" class="tr-caption-container" style="margin-left: auto; margin-right: auto; text-align: center;"><tbody>
<tr><td style="text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj-e9l_BKHlKdRFS5WLyJ7i0vu0utk4RApukfMn_0dsYJZTa_oL49c6KN8JS0uAM7ZgqQfeb-60QgjXY_WJoUW1lhGVL7Y7BKV0T5fnQz8Fuc-SuoSK0HykVcWxA_S1VtaK4SfLjPPxBV2z/s1600/rdaScen1.png" imageanchor="1" style="margin-left: auto; margin-right: auto;"><img border="0" data-original-height="782" data-original-width="1000" height="250" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj-e9l_BKHlKdRFS5WLyJ7i0vu0utk4RApukfMn_0dsYJZTa_oL49c6KN8JS0uAM7ZgqQfeb-60QgjXY_WJoUW1lhGVL7Y7BKV0T5fnQz8Fuc-SuoSK0HykVcWxA_S1VtaK4SfLjPPxBV2z/s320/rdaScen1.png" width="320" /></a></td></tr>
<tr><td class="tr-caption" style="text-align: center;">RDA "Scenario 1" data design, 2009</td></tr>
</tbody></table>
In the early days of the catalog we had a separate file and interface for the cataloged serials based on a statewide project (including the California State Universities). Although it was possible to catalog serials in the MARC format, the systems that had the detailed information about which issues the libraries held was stored in serials control databases that were separate from the library catalog, and many serials were represented by crusty cards that had been created decades before library automation. The group below developed and managed the CALLS (California Academic Library List of Serials). Four of those pictured were programmers, two were serials data specialists, and four had library degrees. Obviously, these are overlapping sets. The project heads were Barbara Radke (right) and Theresa Montgomery (front, second from right).<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEihZ8cZMZ3e3sKq2nrDKxpOGwpINq3-3itKTaCJnbhgEY2vulm4OqB5WasDDKxYHPq3fgqQMgwgjxHzIpKSzwnHIqIjqrPGxhIPU_bpYrw02Rb7WBwuP3PWlY267LbpDp1gTCuZKyep6qot/s1600/calls.jpg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="1200" data-original-width="1600" height="240" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEihZ8cZMZ3e3sKq2nrDKxpOGwpINq3-3itKTaCJnbhgEY2vulm4OqB5WasDDKxYHPq3fgqQMgwgjxHzIpKSzwnHIqIjqrPGxhIPU_bpYrw02Rb7WBwuP3PWlY267LbpDp1gTCuZKyep6qot/s320/calls.jpg" width="320" /></a></div>
At one point while I was still working on the MELVYL project, but probably around the very late 1990's or early 2000's, I gathered up some organization charts that had been issued over the years and quickly calculated that during its history the project the technical staff that had created this early marvel had varied from 3/4 to 2/3 female. I did some talks at various conferences in which I called MELVYL a system "created by women." At my retirement in 2003 I said the same thing in front of the entire current staff, and it was not well-received by all. In that audience was one well-known member of the profession who later declared that he felt women needed more mentoring in technology because he had always worked primarily with men, even though he had indeed worked in an organization with a predominantly female technical staff, and another colleague who was incredulous when I stated once that women are not a minority, but over 50% of the world's population. He just couldn't believe it.<br />
<br />
While outright discrimination and harassment of women are issues that need to be addressed, the invisibility of women in the eyes of their colleagues and institutions is horribly damaging. There are many interesting projects, not the least the <a href="https://en.wikipedia.org/wiki/Wikipedia:WikiProject_Women_in_Red" target="_blank">Wikipedia Women in Red</a>, that aim to show that there is no lack of accomplished women in the world, it's the acknowledgment of their accomplishments that falls short. In the library profession we have many women whose stories are worth telling. Please, let's make sure that future generations know that they have foremothers to look to for inspiration.Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com1tag:blogger.com,1999:blog-3338174527262061848.post-19978664339971048752020-05-25T06:25:00.000-07:002020-05-25T06:25:19.630-07:001982I've been trying to capture what I remember about the early days of library automation. Mostly my memory is about fun discoveries in my particular area (processing MARC records into the online catalog). I did run into an offprint of some articles in ITAL from 1982 (*) which provide very specific information about the technical environment, and I thought some folks might find that interesting. This refers to the University of California MELVYL union catalog, which at the time had about 800,000 records.<br />
<br />
<b>Operating system:</b> IBM 360/370<br />
<b>Programming language:</b> PL/I<br />
<b>CPU: </b>24 megabytes of memory<br />
<b>Storage:</b> 22 disk drives, ~ 10 gigabytes<br />
<b>DBMS:</b> ADABAS<br />
<br />
The disk drives were each about the size of an industrial washing machine. In fact, we referred to the room that held them as "the laundromat." <br />
<br />
Telecommunications was a big deal because there was no telecommunications network linking the libraries of the University of California. There wasn't even one connecting the campuses at all. The article talks about the various possibilities, from an <i>X.25 network</i> to the new <i>TCP/IP protocol</i> that allows "internetwork communication." The first network was a set of dedicated lines leased from the phone company that could transmit <i>120 characters per second </i>(character = byte) to about 8 <i>ASCII terminals</i> at each campus over a <i>9600 baud</i> line. There was a hope to be able to double the number of terminals.<br />
<br />
In the speculation about the future, there was doubt that it would be possible to open up the library system to folks outside of the UC campuses, much less internationally. (MELVYL was one of the early libraries to be open access worldwide over the Internet, just a few years later.) It was also thought that libraries would charge other libraries to view their catalogs, kind of like an inter-library loan.<br />
<br />
And for anyone who has an interest in Z39.50, one section of the article by David Shaughnessy and Clifford Lynch on telecommunications outlines a need for catalog-to-catalog communication which sounds very much like the first glimmer of that protocol.<br />
<br />
-----<br />
<br />
(*) Various authors in a special edition: <span class="citation">(1982). In-Depth: University of California MELVYL. <cite>Information Technology and Libraries, 1</cite>(4)</span><br />
<br />
<span class="citation">I wish I could give a better citation but my offprint does not have page numbers and I can't find this indexed anywhere. (Cue here the usual irony that libraries are terrible at preserving their own story.) </span><br />
<br />Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com0tag:blogger.com,1999:blog-3338174527262061848.post-67197856113531358952020-04-27T08:08:00.000-07:002020-04-27T08:08:28.180-07:00Ceci n'est pas une BibliothèqueOn March 24, 2020, the Internet Archive <a href="http://blog.archive.org/2020/03/24/announcing-a-national-emergency-library-to-provide-digitized-books-to-students-and-the-public/" target="_blank">announced</a> that it would "suspend waitlists for the 1.4 million (and growing) books in our lending library," a service they then named <a href="https://archive.org/details/nationalemergencylibrary" target="_blank">The National Emergency Library</a>. These books were previously available for lending on a one-to-one basis with the physical book owned by the Archive, and as with physical books users would have to wait for the book to be returned before they could borrow it. Worded as a suspension of waitlists due to the closure of schools and libraries caused by the presence of the coronavirus-19, this announcement essentially eliminated the one-to-one nature of the Archive's <a href="https://en.wikipedia.org/wiki/Controlled_digital_lending" target="_blank">Controlled Digital Lending</a> program. Publishers were already making <a href="https://newsroom.publishers.org/statement-on-flawed-theory-of-controlled-digital-lending/" target="_blank">threatening noises</a> about the digital lending when it adhered to lending limitations, and surely will be even more incensed about this unrestricted lending.<br />
<br />
I am not going to comment on the legality of the Internet Archive's lending practices. Legal minds, perhaps motivated by future lawsuits, will weigh in on that. I do, however, have much to say on the use of the term "library" for this set of books. It's a topic worthy of a lengthy treatment, but I'll give only a brief account here.<br />
<br />
<h3 class="part" data-endline="3" data-startline="3">
LIBRARY … BIBLIOTHÈQUE … BIBLIOTEK </h3>
<div class="part" data-endline="5" data-startline="5">
<br />
The
roots “LIBR…” and “BIBLIO…” both come down to us from ancient words for
trees and tree bark. It is presumed that said bark was the surface for
early writings. “LIBR…”, from the Latin word <i>liber</i> meaning
“book,” in many languages is a prefix that indicates a bookseller’s
shop, while in English it has come to mean a collection of books and
from that also the room or building where books are kept. “BIBLIO…”
derives instead from the Greek <i>biblion</i> (one book) and <i>biblia</i> (books, plural). We get the word Bible through the Greek root, which leaked into old Latin and meant The Book.</div>
<br />
Therefore it is no wonder that in the minds of many people, books = library. In fact, most libraries are large collections of books, but that does not mean that every large collection of books is a library. Amazon has a large number of books, but is not a library; it is a store where books are sold. Google has quite a few books in its "book search" and even allows you to view portions of the books without payment, but it is also not a library, it's a search engine. The Internet Archive, Amazon, and Google all have catalogs of metadata for the books they are offering, some of it taken from actual library catalogs, but a catalog does not make a quantity of books into a library. After all, Home Depot has a catalog, Walmart has a catalog; in essence, any business with an inventory has a catalog.<br />
<blockquote class="tr_bq">
<span style="font-size: large;"><b>"...most libraries are large collections of books, but that does not mean that every large collection of books is a library." </b></span></blockquote>
<h3>
The Library Test</h3>
First, I want to note that the Internet Archive has met the State of California test to be defined as a library, and this has made it possible for the Archive to apply for library-related grants for some of its projects. That is a Good Thing because it has surely strengthened the Archive and its activities. However, it must be said that the State of California requirements are pretty minimal, and seem to be limited to a non-profit organization making materials available to the general public without discrimination. There doesn't seem to be a distinction between "library" and "archive" in the state legal code, although librarians and archivists would not generally consider them easily lumped together as equivalent services. <br />
<br />
<h3>
The Collection</h3>
The Archive's <a href="http://blog.archive.org/2020/04/07/the-national-emergency-library-who-needs-it-who-reads-it-lessons-from-the-first-two-weeks/#comment-393221" target="_blank">blog post</a> says "the Internet Archive currently lends about as many as a US library that serves a population of about 30,000." As a comparison, I found in the statistics gathered by the <a href="https://ca.countingopinions.com/index.php?page_id=3" target="_blank">California State Library</a> those of the Benicia Public Library in Benicia California. Benicia is a city with a population of 31,000; the library has about 88,000 books. Well, you might say, that's not as good as over one million books at the Internet Archive. But, here's the thing: those are not 88,000 random books, they are books chosen to be, as far as the librarians could know, the best books for that small city. If Benicia residents were, for example, primarily Chinese-speaking, the library would surely have many books in Chinese. If the city had a large number of young families then the children's section would get particular attention. The users of the Internet Archive's books are a self-selected (and currently un-defined) set of Internet users. Equally difficult to define is the collection that is available to them:<br />
<blockquote class="tr_bq">
This library brings together all the books from <a href="https://archive.org/details/phillipsacademy">Phillips Academy Andover</a> and <a href="https://archive.org/details/marygrovecollege">Marygrove College</a>, and much of <a href="https://archive.org/details/trent_university">Trent University’s</a>
collections, along with over a million other books donated from other
libraries to readers worldwide that are locked out of their libraries.</blockquote>
Each of these is (or was, in the case of Marygrove, which has closed) a collection tailored to the didactic needs of that institution. How one translates that, if one can, to the larger Internet population is unknown. That a collection has served a specific set of users does not mean that it can serve all users equally well. Then there is that other million books, which are a complete black box.<br />
<br />
<h3>
Library science </h3>
I've argued before against dumping a large and undistinguished set of books on a populace, regardless of the good intentions of those doing so. Why not give the library users of a small city these one million books? The main reason is the ability of the library to fulfill the <a href="http://www.worldcat.org/oclc/614879513" target="_blank"><b>5 Laws of Library Science</b></a>:<br />
<ol>
<li>Books are for use.</li>
<li>Every reader his or her book.</li>
<li>Every book its reader.</li>
<li>Save the time of the reader.</li>
<li>The library is a growing organism. [0]</li>
</ol>
The online collection of the Internet Archive nicely fulfills laws 1 and 5: the digital books are designed for use, and the library can grow somewhat indefinitely. The other three laws are unfortunately hindered by the somewhat haphazard nature of the set of books, combined with the lack of user services.<br />
<br />
Of the goals of librarianship, matching readers to books is the most difficult. Let's start with law 3, "every book its reader." When you follow the URL to the National Emergency Library, you see something like this:<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEicFo8qHy2q4M7dVw-o4oWl6vE75M_BXc_A8zpsBlsZRnXoMw0c5WC2gXh5N1ylUw2uKCbVzEBBDWdgbQlICKrS4jLRSb_vf_zKfeDzvxwDU2QA2eO_nzHMkg0HErDccMS4m-M_r988KcpS/s1600/Screenshot+2020-03-26+08.20.33.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="414" data-original-width="788" height="168" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEicFo8qHy2q4M7dVw-o4oWl6vE75M_BXc_A8zpsBlsZRnXoMw0c5WC2gXh5N1ylUw2uKCbVzEBBDWdgbQlICKrS4jLRSb_vf_zKfeDzvxwDU2QA2eO_nzHMkg0HErDccMS4m-M_r988KcpS/s320/Screenshot+2020-03-26+08.20.33.png" width="320" /></a></div>
The lack of cover art is not the problem here. Look at what books you find: two meeting reports, one journal publication, and a book about hand surgery, all from 1925. Scroll down for a bit and you will find it hard to locate items that are less obscure than this, although undoubtedly there are some good reads in this collection. These are not the books whose readers will likely be found in our hypothetical small city. These are books that even some higher education institutions would probably choose not to have in their collections. While these make the total number of available books large, they may not make the total number of <i>useful</i> books large. Winnowing this set to one or more (probably more) wheat-filled collections could greatly increase the usability of this set of books.<br />
<br />
<blockquote class="tr_bq">
<span style="font-size: large;"><b>"While these make the total number of available books large, they may not make the total number of <i>useful</i> books large."</b></span> </blockquote>
<br />
A large "anything goes" set of documents is a real challenge for laws 2 and 4: <i>every reader his or her book,</i> and <i>save the time of the reader</i>. The more chaff you have the harder it is for a library user to find the wheat they are seeking. The larger the collection the more of the burden is placed on the user to formulate a targeted search query and to have the background to know which items to skip over. The larger the retrieved set, the less likely that any user will scroll through the entire display to find the best book for their purposes. This is the case for any large library catalog, but these libraries have built their collection around a particular set of goals. Those goals matter. Goals are developed to address a number of factors, like:<br />
<ul>
<li>What are the topics of interest to my readers and my institution?</li>
<li>How representative must my collection be in each topic area?</li>
<li>What are the essential works in each topic area? </li>
<li>What depth of coverage is needed for each topic? [1]</li>
</ul>
If we assume (and we absolutely must assume this) that the user entering the library is seeking information that he or she lacks, then we cannot expect users to approach the library as an expert in the topic being researched. Although anyone can type in a simple query, fewer can assess the validity and the scope of the results. A search on "California history" in the National Emergency Library yields some interesting-looking books, but are these the best books on the topic? Are any key titles missing? These are the questions that librarians answer when developing collections.<br />
<br />
The creation of a well-rounded collection is a difficult task. There are actual measurements that can be run against library collections to determine if they have the coverage that can be expected compared to similar libraries. I don't know if any such statistical packages can look beyond quantitative measures to judge the quality of the collection; the ones I'm aware of look at call number ranges, not individual titles. There <br />
<br />
<h3>
Library Service</h3>
<br />
The Archive's <a href="https://help.archive.org/hc/en-us/articles/360004716051-Internet-Archive-General-Information" target="_blank">own documentation</a> states that "The Internet Archive focuses on preservation and providing access to
digital cultural artifacts. For assistance with research or appraisal,
you are bound to find the information you seek elsewhere on the
internet." After which it advises people to get help through their local public library. Helping users find materials suited to their need is a key service provided by libraries. When I began working in libraries in the dark ages of the 1960's, users generally entered the library and went directly to the reference desk to state the question that brought them to the institution. This changed when catalogs went online and were searchable by keyword, but prior to then the catalog in a public library was primarily a tool for librarians to use when helping patrons. Still, libraries have real or virtual reference desks because users are not expected to have the knowledge of libraries or of topics that would allow them to function entirely on their own. And while this is true for libraries it is also true, perhaps even more so, for archives whose collections can be difficult to navigate without specialized information. Admitting that you give no help to users seeking materials makes the use of the term "library" ... unfortunate.<br />
<br />
<h3>
What is to be done?</h3>
<br />
There are undoubtedly a lot of useful materials among the digital books at the Internet Archive. However, someone needing materials has no idea whether they can expect to find what they need in this amalgamation. The burden of determining whether the Archive's collection might suit their needs is left entirely up to the members of this very fuzzy set called "Internet users." That the collection lends at the rate of a public library serving a population of 30,000 shows that it is most likely under-utilized. Because the nature of the collection is unknown one can't approach, say, a teacher of middle-school biology and say: "they've got what you need." Yet the Archive cannot implement a policy to complete areas of the collection unless it knows what it has as compared to known needs.<br />
<br />
<blockquote class="tr_bq">
<b><span style="font-size: large;">"... these warehouses of potentially readable text will remain under-utilized
until we can discover a way to make them useful in the ways that
libraries have proved to be useful." </span></b> </blockquote>
<br />
I wish I could say that a solution would be simple - but it would not. For example, it would be great to extract from this collection works that are commonly held in specific topic areas in small, medium and large libraries. The statistical packages that analyze library holdings all are, AFAIK, proprietary. (If anyone knows of an open source package that does this, please shout it out!) If would also be great to be able to connect library collections of analog books to their digital equivalents. That too is more complex than one would expect, and would have to be much simpler to be offered openly. [2]<br />
<br />
While some organizations move forward with digitizing books and other hard copy materials, these warehouses of potentially readable text will remain under-utilized until we can discover a way to make them useful in the ways that libraries have proved to be useful. This will mean taking seriously what modern librarianship has developed over its circa 2 centuries, and in particular those 5 laws that give us a philosophy to guide our vision of service to the users of libraries.<br />
<br />
-----<br />
<br />
[0] Even if you are familiar with the 5 laws you may not know that Ranganathan was not as succinct as this short list may imply. The book in which he introduces these concepts is over 450 pages long, with extended definitions and many homey anecdotes and stories. <br />
<br />
[1] A search on "collection development policy" will yield many pages of policies that you can peruse. To make this a "one click" here are a few *non-representative* policies that you can take a peek at:<br />
<ul>
<li><a href="https://www.hclib.org/about/policies/collection-development-and-management" target="_blank">Hennepin County</a> (public)</li>
<li><a href="https://lcc.edu/library/about/collection.html" target="_blank">Lansing Community College</a> (community college)</li>
<li><a href="https://library.stanford.edu/science/collections/chemistry-and-chemical-engineering-collection/collection-development-policy" target="_blank">Stanford University, Science Library</a> (research library)</li>
</ul>
[2] <a href="https://coffeecode.net/" target="_blank">Dan Scott</a> and I did a project of this nature with a Bay Area public library and it took a huge amount of human intervention to determine whether the items matched were really "equivalent". That's a discussion for another time, but, man, books are more complicated than they appear.Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com0tag:blogger.com,1999:blog-3338174527262061848.post-22092259713844611262020-02-03T06:59:00.002-08:002020-02-03T06:59:59.874-08:00Use the Leader, Luke!If you learned the MARC format "on the job" or in some other library context you may have learned that the record is structured as fields with 3-digit tags, each with two numeric indicators, and that subfields have a subfield indicator (often shown as "$" because it is a non-printable character) and a single character subfield code (a-z, 0-9). That is all true for the MARC records that libraries create and process, but the MAchine Readable Cataloging standard (Z39.2 or ISO 2709) has other possibilities that we are not using. Our "MARC" (currently MARC21) is a single selection from among those possibilities, in essence an application profile of the MARC standard. The key to the possibilities afforded by MARC is in the MARC Leader, and in particular in two positions that our systems generally ignore because they always contain the same values in our data:<br />
<blockquote class="tr_bq">
Leader byte 10 -- Indicator count<br />
Leader byte 11 -- Subfield code length</blockquote>
In MARC21 records, Leader byte 10 is always "2" meaning that fields have 2-byte indicators, and Leader byte 11 is always 2 because the subfield code is always two characters in length. That was a decision made early on in the life of MARC records in libraries, and it's easy to forget that there were other options that were not taken. Let's take a short look at the possibilities the record format affords beyond our choice.<br />
<br />
Both of these Leader positions are single bytes that can take values from 0 to 9. An application could use the MARC record format and have zero indicators. It isn't hard to imagine an application that has no need of indicators or that has determined to make use of subfields in their stead. As an example, the provenance of vocabulary data for thesauri like LCSH or the Art and Architecture Thesaurus could always be coded in a subfield rather than in an indicator:<br />
<blockquote class="tr_bq">
650 $a Religion and science $2 LCSH</blockquote>
Another common use of indicators in MARC21 is to give a byte count for the non-filing initial articles on title strings. Istead of using an indicator value for this some libraries outside of the US developed a non-printing code to make the beginning and end of the non-filing portion. I'll use backslashes to represent these codes in this example:<br />
<blockquote class="tr_bq">
245 $a \The \Birds of North America</blockquote>
I am not saying that all indicators in MARC21 should or even could be eliminated, but that we shouldn't assume that our current practice is the only way to code data.<br />
<br />
In the other direction, what if you could have more than two indicators? The MARC record would allow you have have as many as nine. In addition, there is nothing to say that each byte in the indicator has to be a separate data element; you could have nine indicator positions that were defined as two data elements (4 + 5), or some other number (1 + 2 + 6). Expanding the number of indicators, or beginning with a larger number, could have prevented the split in provenance codes for subject vocabularies between one indicator value and the overflow subfield, $2, when the number exceeded the capability of a single numerical byte. Having three or four bytes for those codes in the indicator and expanding the values to include a-z would have been enough to include the full list of authorities for the data in the indicators. (Although I would still prefer putting them all in $2 using the mnemonic codes for ease of input.)<br />
<br />
In the first University of California union catalog in the early 1980's we expanded the MARC indicators to hold an additional two bytes (or was it four?) so that we could record, for each MARC field, which library had contributed it. Our union catalog record was a composite MARC record with fields from any and all of the over 300 libraries across the University of California system that contributed to the union catalog as dozen or so separate record feeds from OCLC and RLIN. We treated the added indicator bytes as sets of bits, turning on bits to represent the catalog feeds from the libraries. If two or more libraries submitted exactly the same MARC field we stored the field once and turned on a bit for each separate library feed. If a library submitted a field for a record that was new to the record, we added the field and turned on the appropriate bit. When we created a user display we selected fields from only one of the libraries. (The rules for that selection process were something of a secret so as not to hurt anyone's feelings, but there was a "best" record for display.) It was a multi-library MARC record, made possible by the ability to use more than two indicators.<br />
<br />
Now on to the subfield code. The rule for MARC21 is that there is a single subfield code and that is a lower case a-z and 0-9. The numeric codes have special meaning and do not vary by field; the alphabetic codes aare a bit more flexible. That gives use 26 possible subfields per tag, plus the 10 pre-defined numeric ones. The MARC21 standard has chosen to limit the alphabetic subfield codes to lower case characters. As the fields reached the limits of the available subfield codes (and many did over time) you might think that the easiest solution would be to allow upper case letters as subfield codes. Although the subfield code limitation was reached decades ago for some fields I can personally attest to the fact that suggesting the expansion of subfield codes to upper case letters was met with horrified glares at the MARC standards meeting. While clearly in 1968 the range of a-z seemed ample, that has not be the case for nearly half of the life-span of MARC.<br />
<br />
The MARC Leader allows one to define up to 9 characters total for subfield codes. The value in this Leader position includes the subfield delimiter so this means that you can have a subfield delimiter and up to 8 characters to encode a subfield. Even expanding from a-z to aa-zz provides vastly more possibilities, and allow upper case as well give you a dizzying array of choices. <br />
<br />
The other thing to mention is that there is no prescription that field tags must be numeric. They are limited to three characters in the MARC standard, but those could be a-z, A-Z, 0-9, not just 0-9, greatly expanding the possibilities for adding new tags. In fact, if you have been in the position to view internal systems records in your vendor system you may have been able to see that non-numeric tags have been used for internal system purposes, like noting who made each edit, whether functions like automated authority control have been performed on the record, etc. Many of the "violations" of the MARC21 rules listed here have been exploited internally -- and since early days of library systems.<br />
<br />
There are other modifiable Leader values, in particular the one that
determines the maximum length of a field, Leader 20. MARC21 has Leader
20 set at "4" meaning that fields cannot be longer than 9999. That could
be longer, although the record size itself is set at only 5 bytes, so a
record cannot be longer than 99999. However, one could limit fields to
999 (Leader value 20 set at "3") for an application that does less
pre-composing of data compared to MARC21 and therefore comfortably fits
within a shorter field length. <br />
<br />
The reason that has been given, over time, why none of these changes were made was always: it's too late, we can't change our systems now. This is, as Caesar might have said, <i>cacas tauri</i>. Systems have been able to absorb some pretty intense changes to the record format and its contents, and a change like adding more subfield codes would not be impossible. The problem is not really with the MARC21 record but with our inability (or refusal) to plan and execute the changes needed to evolve our systems. We could sit down today and develop a plan and a timeline. If you are skeptical, here's an example of how one could manage a change in length to the subfield codes:<br />
<br />
a MARC21 record is retrieved for editing<br />
<ol>
<li>read the Leader 10 of the MARC21 record</li>
<li>if the value is "2" and you need to add a new subfield that uses the subfield code plus two characters, convert all of the subfield codes in the record:</li>
<ul>
<li>$a becomes $aa, $b becomes $ba, etc.</li>
<li>$0 becomes $01, $1 becomes $11, etc.</li>
<li>Leader 10 code is changed to "3" </li>
</ul>
<li>(alternatively, convert all records opened for editing)</li>
</ol>
<br />
a MARC21 record is retrieved for display<br />
<ol>
<li>read the Leader 10 of the MARC21 record</li>
<li>if the value is "2" use the internal table of subfield codes for records with the value "2"</li>
<li>if the value is "3" use the internal table of subfield codes for records with the value "3"</li>
</ol>
<br />
Sounds impossible? We moved from AACR to AACR2, and now from AACR2 to RDA without going back and converting all of our records to the new content. We have added new fields to our records, such as the 336, 337, 338 for RDA values, without converting all of the earlier records in our files to have these fields. The same with new subfields, like $0, which has only been added in recent years. Our files have been using mixed record types for at least a couple of generations -- generations of systems and generations of catalogers.<br />
<br />
Alas, the time to make these kinds of changes this was many years ago. Would it be worth doing today? That depends on whether we anticipate a change to BIBFRAME (or some other data format) in the near future. Changes do continue to be made to the MARC21 record; perhaps it would have a longer future if we could broach the subject of fixing some of the errors that were introduced in the past, in particular those that arose because of the limitations of MARC21 that could be rectified with an expansion of that record standard. That may also help us not carry over some of the problems in MARC21 that are caused by these limitations to a new record format that does not need to be limited in these ways.<br />
<br />
<h4>
Epilogue</h4>
<br />
Although the MARC record was incredibly advanced compared to other data formats of its time (the mid-1960's), it has some limitations that cannot be overcome within the standard itself. One obvious one is the limitation of the record length to 5 bytes. Another is the fact that there are only two levels of nesting of data: the field and the subfield. There are times when a sub-subfield would be useful, such as when adding information that relates to only one subfield, not the entire field (provenance, external URL link). I can't advocate for continuing the data format that is often called "binary MARC" simply because it has limitations that require work-arounds. MARCXML, as defined as a standard, gets around the field and record length limitations, but it is not allowed to vary from the MARC21 limitations on field and subfield coding. It would be incredibly logical to move to a "non-binary" record format (XML, JSON, etc.) beginning with the existing MARC21 and to allow expansions where needed. It is the stubborn adherence to the ISO 2709 format really has limited library data, and it is all the more puzzling because other solutions that can keep the data itself intact have been available for many decades. Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com0tag:blogger.com,1999:blog-3338174527262061848.post-16938851596239708962020-01-28T13:15:00.000-08:002020-01-28T13:15:25.991-08:00PamfletsI was always a bit confused about the inclusion of "pamflets" in the subtitle of the Decimal System, such as this title page from the 1922 edition:<br />
<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiHjsBIhlrhBgrY4NjAL-kWFUk0nzd-hOFDg-OtkbEDjeSjj9IzOd6lyWwJ_Iq0ztxAE9bW4gzMsnNjvMfGA1FX29MmbERYOSPZq2wwaDGAOEobt0hyphenhyphen7vvaEuLm-RQcZiluoUUV49EA6uIk/s1600/pamfletsDDC.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="410" data-original-width="481" height="272" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiHjsBIhlrhBgrY4NjAL-kWFUk0nzd-hOFDg-OtkbEDjeSjj9IzOd6lyWwJ_Iq0ztxAE9bW4gzMsnNjvMfGA1FX29MmbERYOSPZq2wwaDGAOEobt0hyphenhyphen7vvaEuLm-RQcZiluoUUV49EA6uIk/s320/pamfletsDDC.png" width="320" /></a></div>
Did libraries at the time collect numerous pamphlets? For them to be the second-named type of material after books was especially puzzling.<br />
<br />
I may have discovered an answer to my puzzlement, if not THE answer, in <a href="https://en.wikipedia.org/wiki/Andrea_Crestadoro" target="_blank">Andrea Costadoro</a>'s 1856 <a href="http://www.worldcat.org/oclc/462276333" target="_blank">work</a>:<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEibcnpFozNpIyKbvh4byyi5hUgdaZE0UVTJoGJZGelgVWfNhyphenhyphenZRT5Hvl13M86BYyqEG9VJYDRatWLQt6cWlOXCWOjnEHyIuxjMoYqXDPQQQ1052_Ul2dFdd2fAUugPgUZPp4jlyZRtH3YMv/s1600/crestadoro-titlepage.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="175" data-original-width="463" height="120" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEibcnpFozNpIyKbvh4byyi5hUgdaZE0UVTJoGJZGelgVWfNhyphenhyphenZRT5Hvl13M86BYyqEG9VJYDRatWLQt6cWlOXCWOjnEHyIuxjMoYqXDPQQQ1052_Ul2dFdd2fAUugPgUZPp4jlyZRtH3YMv/s320/crestadoro-titlepage.png" width="320" /></a></div>
A "pamphlet" in 1856 was not (necessarily) what I had in mind, which was a flimsy publication of the type given out by businesses, tourist destinations, or public health offices. In the 1800's it appears that a pamphlet was a literary type, not a physical format. Costadoro says:<br />
<blockquote class="tr_bq">
"It has been a matter of discussion what books should be considered pamphlets and what not. If this appellation is intended merely to refer to the SIZE of the book, the question can be scarecely worth considering ; but if it is meant to refer to the NATURE of a work, it may be considered to be of the same class and to stand in the same connexion with the word <i>Treatise</i> as the words <i>Tract</i> ; <i>Hints</i> ; <i>Remarks</i> ; &c, when these terms are descriptive of the nature of the books to which they are affixed." (p. 42)</blockquote>
To be on the shelves of libraries, and cataloged, it is possible that these pamphlets were indeed bound, perhaps by the library itself. <br />
<br />
The Library of Congress genre list today has a cross-reference from "pamphlet" to <a href="http://id.loc.gov/authorities/genreForms/gf2015026053.html" target="_blank">"Tract (ephemera)"</a>. While Costadoro's definition doesn't give any particular subject content to the type of work, LC's definition says that these are often issued by religious or political groups for proselytizing. So these are pamphlets in the sense of the political pamphlets of our revolutionary war. Today they would be blog posts, or articles in Buzzfeed or Slate or any one of hundreds of online sites that post such content.<br />
<br />
Churches I have visited often have short publications available near the entrance, and there is always the <a href="https://en.wikipedia.org/wiki/The_Watchtower" target="_blank">Watchtower</a>,
distributed by Jehovah's Witnesses at key locations throughout the
world, and which is something between a pamphlet (in the modern sense)
and a journal issue. These are probably not gathered in most libraries
today. In Dewey's time the printing (and collecting by
libraries) of sermons was quite common. In a world where many people either were not literate or did not have access to much reading material, the Sunday sermon was a "long form" work, read by a pastor who was probably not as eloquent as the published "stars" of the Sunday gatherings. Some sermons were brought together into
collections and published, <a href="https://openlibrary.org/works/OL18109525W" target="_blank">others</a> were published (and seemingly bound) on their own. Dewey is often
criticized for the bias in his classification, but what you find in the
early editions serves as a brief overview of the printed materials that
the US (and mostly East Coast) culture of that time valued. <br />
<br />
What now puzzles me is what took the place of these tracts between the time of Dewey and the Web. I can find archives of political and cultural pamphlets in various countries and they
all seem to end around the 1920's-30's, although some specific
collections, such as the Samizdat publications in the Soviet Union,
exist in other time periods. <br />
<br />
Of course the other question now is: how many of today's tracts and treatises will survive if they are not published in book form? Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com0tag:blogger.com,1999:blog-3338174527262061848.post-85930995296055434812019-11-23T04:13:00.000-08:002019-11-23T04:13:22.976-08:00The WorkThe word "<a href="https://www.merriam-webster.com/dictionary/work" target="_blank">work</a>" generally means something brought about by human effort, and at times implies that this effort involves some level of creativity. We talk about "works of art" referring to paintings hanging on walls. The "works" of Beethoven are a large number of musical pieces that we may have heard. The "works" of Shakespeare are plays, in printed form but also performed. In these statements the "work" encompasses the whole of the thing referred to, from the intellectual content to the final presentation. <br />
<br />
This is not the same use of the term as is found in the Library Reference Model (<a href="https://www.ifla.org/publications/node/11412" target="_blank">LRM</a>). If you are unfamiliar with the LRM, it is the successor to FRBR (which I am assuming you have heard of) and it includes the basic concepts of work, expression, manifestation and item that were first introduced in that previous study. "Work," as used in the LRM is a concept designed for use in library cataloging data. It is narrower than the common use of the term illustrated in the previous paragraph and is defined thus:<br />
<blockquote class="tr_bq">
Class: Work<br />
Definition: An abstract notion of an artistic or intellectual creation.</blockquote>
In this definition the term only includes the idea of a non-corporeal conceptual entity, not the totality that would be implied in the phrase "the works of Shakespeare." That totality is described when the work is realized through an LRM-defined "expression" which in turn is produced in an LRM-defined "manifestation" with an LRM-defined "item" as its instance.* These four entities are generally referred to as a group with the acronym WEMI.<br />
<br />
Because many in the library world are very familiar with the LRM definition of work, we have to use caution when using the word outside the specific LRM environment. In particular, we must not impose the LRM definition on uses of the work that are not intending that meaning. One should expect that the use of the LRM definition of work would be rarely found in any conversation that is not about the library cataloging model for which it was defined. However, it is harder to distinguish uses within the library world where one might expect the use to be adherent to the LRM. <br />
<br />
To show this, I want to propose a particular use case. Let's say that a very large bibliographic database has many records of bibliographic description. The use case is that it is deemed to be easier for users to navigate that large database if they could get search results that cluster works rather than getting long lists of similar or nearly identical bibliographic items. Logically the cluster looks like this:<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhW5FDpraJNk7TQDBbbTALtnX_24_8Qh3kLMf-Ajs90d1uKmW6kpXsnea0HpFL6Z7UOthgphgg2woElQy4RpCqwqbfubW5PXbNFWRW3JCwA3RLmK4t20E135m6ZluhZrhXgZZzh-7FQi7a5/s1600/Slide2.jpeg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="405" data-original-width="720" height="225" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhW5FDpraJNk7TQDBbbTALtnX_24_8Qh3kLMf-Ajs90d1uKmW6kpXsnea0HpFL6Z7UOthgphgg2woElQy4RpCqwqbfubW5PXbNFWRW3JCwA3RLmK4t20E135m6ZluhZrhXgZZzh-7FQi7a5/s400/Slide2.jpeg" width="400" /></a></div>
<br />
<br />
In data design, it will have a form something like this:<br />
<div class="separator" style="clear: both; text-align: center;">
</div>
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgWQLn6EJ_BlF1nEYXz5wuhyphenhyphenZdFA2NZlMpt8JfpOaq3DVq8TMvRm4oUo9RqnLHMQmcqTC7nLnI6T8-zkuzxiGVTy1UeMmytEnO5vLNgz0Bt6c7YW2wl2ZCvNI30dHuT88nC6H3vMJ4jupPx/s1600/work2.png" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="864" data-original-width="1600" height="215" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgWQLn6EJ_BlF1nEYXz5wuhyphenhyphenZdFA2NZlMpt8JfpOaq3DVq8TMvRm4oUo9RqnLHMQmcqTC7nLnI6T8-zkuzxiGVTy1UeMmytEnO5vLNgz0Bt6c7YW2wl2ZCvNI30dHuT88nC6H3vMJ4jupPx/s400/work2.png" width="400" /></a></div>
<br />
This is a great idea, and it does appear to have a similarity to the LRM definition of work: it is gathering those bibliographic entries that are judged to represent the same intellectual content. However, there are reasons why the LRM-defined work could not be used in this instance. <br />
<br />
The first is that there is only one WEMI relationship for work, and that is from LRM work to LRM expression. Clearly the bibliographic records in this large library catalog are not LRM expressions; they are full bibliographic descriptions including, potentially, all of the entities defined in the LRM.<br />
<br />
To this you might say: but there is expression data in the bibliographic record, so we can think of this work as linking to the expression data in that record. That leads us to the second reason: the entities of WEMI are defined as being disjoint. That means that no single "thing" can be more than one of those entities; nothing can be simultaneously a work and an expression, or any other combination of WEMI entities. So if the only link we have available in the model is from work to expression, unless we can somehow convince ourselves that the bibliographic record ONLY represents the expression (which it clearly does not since it has data elements from at least three of the LRM entities) any such link will violate the rule of disjointness.<br />
<br />
Therefore, the work in our library system can have much in common with the conceptual definition of the LRM work, but it is not the same work entity as is defined in that model. <br />
<br />
This brings me back to my earlier blog post with a <a href="http://kcoyle.blogspot.com/2019/01/frbr-without-fr-or-br.html" target="_blank">proposal</a> for a generalized definition of WEMI-like entities for created works. The WEMI concepts are useful in practice, but the LRM model has some constraints that prevent some desirable uses of those entities. Providing unconstrained entities would expand the utility of the WEMI concepts both within the library community, as evidenced by the use case here, and in the non-library communities that I highlight in that <a href="http://kcoyle.blogspot.com/2019/01/frbr-without-fr-or-br.html" target="_blank">previous blog post</a> and in a <a href="http://kcoyle.net/WEMIpres.pdf" target="_blank">slide presentation</a>.<br />
<br />
To be clear, "unconstrained" refers not only to the removal of the disjointness between entities, but also to allow the creation of links between the WEMI entities and non-WEMI entities, something that is not anticipated in the LRM. The work cluster of bibliographic records would need a general relationship, perhaps, as in the case of VIAF, linked through a shared cluster identifier and an entity type identifying the cluster as representing an unconstrained work. <br />
<br />
----<br />
* The other terms are defined in the LRM as:<br />
<br />
Class: Expression<br />
Definition: A realization of a single work usually in a physical form.<br />
<br />
Class: Manifestation<br />
Definition: The physical embodiment of one or more expressions.<br />
<br />
Class: Item<br />
Definition: An exemplar of a single manifestation.Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com0tag:blogger.com,1999:blog-3338174527262061848.post-71511665312231072642019-04-08T00:30:00.000-07:002019-07-29T07:12:18.985-07:00I, too, want answersAround 1966-67 I worked on the reference desk at my local public library. For those too young to remember, this was a time when all information was in paper form, and much of that paper was available only at the library. The Internet was just a twinkle in the eye of some scientists at DARPA, and none of us had any idea what kind of information environment was in our future.* The library had a card catalog and the latest thing was that check-outs were somehow recorded on microfilm, as I recall.<br />
<br />
As you entered the library the reference desk was directly in front of you in the prime location in the middle of the main room. A large number of library users went directly to the desk upon entering. Some of these users had a particular research in mind: a topic, an author, or a title. They came to the reference desk to find the quickest route to what they sought. The librarian would take them to the card catalog, would look up the entry, and perhaps even go to the shelf with the user to look for the item.**<br />
<br />
There was another type of reference request: a request for facts, not resources. If one wanted to know what was the population of Milwaukee, or how many slot machines there were in Saudia Arabia***, one turned to the library for answers. At the reference desk we had a variety of reference materials: encyclopedias, almanacs, dictionaries, atlases. The questions that we could answer quickly were called "ready reference." These responses were generally factual.<br />
<br />
Because the ready reference service didn't require anything of the user except to ask the question, we also provided this service over the phone to anyone who called in. We considered ourselves at the forefront of modern information services when someone would call and ask us: "Who won best actor in 1937?" OK, it probably was a bar bet or a crossword puzzle clue but we answered, proud of ourselves.<br />
<br />
I was reminded of all this by a recent article in Wired magazine, "Alexa, I Want Answers."[1] The argument as presented in the article is that what people REALLY want is an answer; they don't want to dig through books and journals at the library; they don't even want an online search that returns a page of results; what they want is to ask a question and get an answer, a single answer. What they want is "ready reference" by voice, in their own home, without having to engage with a human being. The article is about the development of the virtual, voice-first, answer machine: Alexa. <br />
<br />
There are some obvious observations to be made about this. The glaringly obvious one is that not all questions lend themselves to a single, one sentence answer. Even a question that can be asked concisely may not have a concise answer. One that I recall from those long-ago days on the reference desk was the question: "When did the Vietnam War begin?" To answer this you would need to clarify a number of things: on whose part? US? France? Exactly what do you mean by begin? First personnel? First troops? Even with these details in hand experts would differ in their answers.<br />
<br />
Another observation is that in the question/answer method over a voice device like Alexa, replying with a lengthy answer is not foreseen. Voice-first systems are backed by databases of facts, not explanatory texts. Like a GPS system they take facts and render them in a way that seems conversational. Your GPS doesn't reply with the numbers of longitude and latitude, and your weather app wraps the weather data in phrases like: "It's 63 degrees outside and might rain later today." It doesn't, however, offer a lengthy discourse on the topic. Just the facts, ma'am.[3]<br />
<br />
It is very troubling that we have no measure of the accuracy of these answers. There are quite a few anecdotes about wrong answers (especially amusing ones) from voice assistants, but I haven't seen any concerted studies of the overall accuracy rate. Studies of this nature were done in the 1970's and 1980's on library reference services, and the results were shocking. Even though library reference was done by human beings who presumably would be capable of detecting wrong answers, the accuracy of answers hovered around 50-60%.[2] Repeated studies came up with similar results, and library journals were filled with articles about this problem. The solution offered was to increase training of reference staff. Before the problem could be resolved, however, users who previously had made use of "ready reference" had moved on to in-sourcing their own reference questions by using the new information system: the Internet. If there still is ready reference occuring in libraries, it is undoubtedly greatly reduced in the number of questions asked, and it doesn't appear that studying the accuracy is on our minds today.<br />
<br />
I have one final observation, and that is that we do not know the source(s) of the information behind the answers given by voice assistants. The companies behind these products have developed databases that are not visible to us, and no source information is given for individual answers. The voice-activated machines themselves are not the main product: they are mere user interfaces, dressed up with design elements that make them appealing as home decor. The data behind the machines is what is being sold, and is what makes the machines useful. With all of the recent discussion of algorithmic bias in artificial intelligence we should be very concerned about where these answers come from, and we should seriously consider if "answers" to some questions are even appropriate or desirable.<br />
<br />
Now, <i><b>I</b></i> have question: how is it possible that so much of our new technology is based on so little intellectual depth? Is reductionism an essential element of technology, or could we do better? I'm not going to ask Alexa**** for an answer to that.<br />
<br />
[1] Vlahos, James. “Alexa, I Want Answers.” Wired, vol. 27, no. 3, Mar. 2019, p. 58. (Try EBSCO)<br />
[2] Weech, Terry L. “Review of The Accuracy of Telephone Reference/Information Services in Academic Libraries: Two Studies.” The Library Quarterly: Information, Community, Policy, vol. 54, no. 1, 1984, pp. 130–31.<br />
[3] https://en.wikipedia.org/wiki/Joe_Friday<br />
<hr />
<br />
* The only computers we saw were the ones on Star Trek (1966), and those were clearly a fiction.<br />
** This was also the era in which the gas station attendent pumped your gas, washed your windows, and checked your oil while you waited in your car. <br />
*** The question about Saudia Arabia is one that I actually got. I also got the one about whether there were many "colored people" in Haiti. I don't remember how I answered the former, but I do remember that the user who asked the latter was quite disappointed with the answer. I think he decided not to go.<br />
**** Which I do not have; I find it creepy even though I can imagine some things for which it could be useful.Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com0tag:blogger.com,1999:blog-3338174527262061848.post-86759761378903437262019-03-12T08:25:00.000-07:002019-03-12T08:25:24.010-07:00I'd like to buy a VOWELOne of the "defects" of RDF for data management is that it does not support business rules. That's a generality, so let me explain a bit. <br />
<br />
Most data is constrained - it has rules for what is and what is not allowed. These rules can govern things like cardinality (is it required? is it repeatable?), value types (date, currency, string, IRI), and data relationships (If A, then not B; either A or B+C). This controlling aspect of data is what many data stores are built around; a bank, a warehouse, or even a library manage their activities through controlled data. <br />
<br />
RDF has a different logical basis. RDF allows you to draw conclusions from the data (called "inferencing") but there is no mechanism of control that would do what we are accustomed to with our current business rules. This seems like such an obvious lack that you might wonder just how the developers of RDF thought it would be used. The answer is that they were not thinking about banking or company databases. The main use case for RDF development was using artificial intelligence-like axioms on the web. That's a very different use case from the kind of data work that most of us engage in. <br />
<br />
RDF is characterized by what is called the "open world assumption" which says that:<br />
<br />
- at any moment a set of data may be incomplete; that does not make it illegitimate<br />
- anyone can say anything about anything; like the web in general there are no controls over what can and cannot be stated and who can participate<br />
<br />
However, RDF is being used in areas where data with controls was once employed; where data is validated for quality and rejected if it doesn't meet certain criteria; where operating on the data is limited to approved actors. This means that we have a mis-match between our data model and some of the uses of that data model.<br />
<br />
This mis-match was evident to people using RDF in their business operations. W3C held a preliminary meeting on "<a href="https://www.w3.org/2012/12/rdf-val/report">Validation of Data Shapes</a>" in which there were presentations over two days that demonstrated some of the solutions that people had developed. This then led to the <a href="https://www.w3.org/2014/data-shapes/charter">Data Shapes working group</a> in 2014 which produced the shapes validation language, <a href="https://www.w3.org/TR/shacl/">SHACL</a> (SHApes Constraint Language) in 2017. Of the interesting ways that people had developed to validate their RDF data, the use of <a href="https://www.w3.org/TR/sparql11-query/">SPARQL</a> searches to determine if expected patterns were met became the basis for SHACL. Another RDF validation language, <a href="http://shex.io/">ShEx</a> (Shape Expressions), is independent of SPARQL but has essentially the same functionality of SHACL. There are other languages as well (<a href="http://spinrdf.org/">SPIN</a>, <a href="https://www.stardog.com/">StarDog</a>, etc.) and they all assume a closed world rather than the open world of RDF.<br />
<br />
My point on all this is to note that we now have a way to validate RDF instance data but no standard way(s) to define our metadata schema, with constraints, that we can use to <i>produce</i> that data. It's kind of a "tail wagging the dog" situation. There have been musings that the validation languages could also be used for metadata definition, but we don't have a proof of concept and I'm a bit skeptical. The reason I'm skeptical is that there's a certain human-facing element in data design and creation that doesn't need to be there in the validation phase. While there is no reason why the validation languages cannot also contain or link to term definitions, cataloging rules, etc. these would be add-ons. The validation languages also do most of their work at the detailed data level, while some guidance for humans happens at the macro definition of a data model - What is this data for? Who is the audience? What should the data creator know or research before beginning? What are the reference texts that one should have access to? While admittedly the <a href="http://access.rdatoolkit.org/">RDA Toolkit</a> used in library data creation is an extreme form of the genre, you can see how much more there is beyond defining specific data elements and their valid values. Using a metadata schema in concert with RDF validation - yes! That's a winning combination, but I think we need bot.<br />
<br />
Note that there are also efforts to use the validation languages to analyze existing graphs.(<a href="https://www.thinkmind.org/download.php?articleid=semapro_2016_4_40_30038">PDF</a>) These could be a quick way to get an overview of data for which you have no description, but the limitations of this technique are easy to spot. They have basically the same problem that AI training datasets do: you only learn what is in that dataset, not the full range of possible graphs and values that can be produced. If your data is very regular then this analysis can be quite helpful; if your data has a lot of variation (as, for example, bibliographic data does) then the analysis of a single file of data may not be terribly helpful. At the same time, exercising the validation languages in this way is one way to discover how we can use algorithms to "look at" RDF data.<br />
<br />
Another thing to note is that there's also quite a bit of "validation" that the validation languages do not handle, such as the reconciliation work that if often done in <a href="http://openrefine.org/">OpenRefine</a>. The validation languages take an atomistic view of the data, not an overall one. I don't see a way to ask the question "Is this entry compatible with all of the other entries in this file?" That the validation languages don't cover this is not a fault, but it must be noted that there is other validation that may need to be done.<br />
<br />
<h3>
WOL, meet WVL</h3>
<h3>
</h3>
We need a data modeling language that is suitable to RDF data, but that provides actual constraints, not just inferences. It also needs to allow one to choose a closed world rule. The RDF suite of standards has provided the Web Ontology Language, which should be WOL but has been given the almost-acronym name of OWL. OWL does define "constraints", but they aren't constraints in the way we need for data creation. OWL constrains the axioms of inference. That means that it gives you rules to use when operating over a graph of data, and it still works in the open world. The use of the term "ontology" also implies that this is a language for the creation of new terms in a single namespace. That isn't required, but that is becoming a practice.<br />
<br />
What we need is a web <i>vocabulary</i> language. WVL. But using the liberty that went from WOL to OWL, we can go from WVL to VWL, and that can be nicely pronounced as VOWEL. VOWEL (I'm going to write it like that because it isn't familiar to readers yet) can supply the constrained world that we need for data creation. It is not necessarily an RDF-based language, but it will use HTTP identifiers for things. It could function as linked data but it also can be entirely in a closed world. Here's what it needs to do:<br />
<ul>
<li>describe the things of the metadata</li>
<li>describe the statements about those things and the values that are valid for those statements</li>
<li>give cardinality rules for things and statements</li>
<li>constrain values by type</li>
<li>give a wide range of possibilities for defining values, such as lists, lists of namespaces, ranges of computable values, classes, etc.</li>
<li>for each thing and statement have the ability to carry definitions and rules for input and decision-making about the value</li>
<li>can be serialized in any language that can handle key/value pairs or triples</li>
<li>can (hopefully easily) be translatable to a validation language or program</li>
</ul>
Obviously there may be more. This is not fully-formed yet, just the beginning. I have defined some of it in a <a href="https://github.com/kcoyle/RDF-AP">github repo</a>. (Ignore the name of the repo - that came from an earlier but related project.) That site also has some other thoughts, such as design patterns, a requirements document, and some comparison between existing proposals, such as the Dublin Core community's Description Set Profile, BIBFRAME, and soon Stanford's profle generator, <a href="http://sinopia.io/">Sinopia</a>. <br />
<br />
One of the ironies of this project is that VOWEL needs to be expressed as a VOWEL. Presumably one could develop an all-new ontology for this, but the fact is that most of what is needed exists already. So this gets meta right off the bat which makes it a bit harder to think about but easier to produce.<br />
<br />
There will be a group starting up in the Dublin Core space to continue development of this idea. I will announce that widely when it happens. I think we have some real possibilities here, to make VOWEL a reality. One of my goals will be to follow the general principles of the original Dublin Core metadata, which is that simple wins out over complex, and it's easier to complex-ify simple than to simplify complex. Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com0tag:blogger.com,1999:blog-3338174527262061848.post-68993137329391574272019-01-28T13:49:00.000-08:002019-01-28T13:49:01.015-08:00FRBR without FR or BR<i>(This is something I started working on that turns out to be a "pulled thread" - something that keeps on unwinding the more I work on it. What's below is a summary, while I decide what to do with the longer piece.)</i><br />
<br />
FRBR was developed for the specific purpose of modeling library catalog data. I give the backstory on FRBR in <a href="http://kcoyle.net/beforeAndAfter/c5-978-0-8389-1364-2.pdf">chapter 5</a> of my book, "<a href="http://kcoyle.net/beforeAndAfter/index.html">FRBR Before and After.</a>" The most innovative aspect of FRBR was the development of a multi-entity view of creative works. Referred to as "group 1" of three groups of entities, the entities described there are Work, Expression, Manifestation, and Item (WEMI). They are aligned with specific bibliographic elements used in library catalogs, and are defined with a rigid structure: the entities are linked to each other in a single chain; the data elements are defined each as being valid for one and only one entity; all WEMI entities are disjoint. <br />
<br />
In spite of these specifics, something in that group 1 has struck a chord for metadata designers who do not adhere to the library catalog model as described in FRBR. In fact, some mentions or uses of WEMI are not even bibliographic in nature.* This leads me to conclude that a version of WEMI that is not tied to library catalog concepts could provide an interesting core of classes for metadata that describes creative or created resources.<br />
<br />
We already have some efforts that have stepped away from the specifics of FRBR. From 2005 there is the first RDF FRBR ontology, <a href="http://vocab.org/frbr/">frbrCore</a>, which defines the entities of FRBR and key relationships between them as RDF classes. This ontology breaks away from FRBR in that it creates super-classes that are not defined in FRBR, but it retains the disjointness between the primary entities. We also have <a href="https://www.ifla.org/publications/node/11240">FRBRoo</a> which is a FRBR-ized version of the CIDOC museum metadata model. This extends the number of classes to include some that represent processes that are not in the static model of the library catalog. In addition we have <a href="https://sparontologies.github.io/fabio/current/fabio.html">FaBiO</a>, a bibliographic ontology that uses frbrCore classes but extends the WEMI-based classes with dozens of sub-classes that represent types of works and expressions.<br />
<br />
I conclude that there is something in the ability to describe the abstraction of work apart from the concrete item that is useful in many areas. The intermediate entities, defined in FRBR as expression and manifestation, may have a role depending on the material and the application for which the metadata is being developed. Other intermediate entities may be useful at times. But as a way to get started, we can define four entities (which are "classes" in RDF) that parallel the four group 1 entities in FRBR. I would like to give these new names to distance them from FRBR, but that may not be possible as people have already absorbed the FRBR terminology.<br />
<br />
<br />
<b>FRBR / option1 / option2</b><br />
work / idea / creative work<br />
expression / creation / realization<br />
manifestation / object / product<br />
item / instance / individual<br />
<br />
My preferred rules for these classes are:<br />
<ul>
<li>any entity can be iterative (e.g. a work of a work)</li>
<li>any entity can have relationships/links to any other entity</li>
<li>no entity has an inherent dependency on any other entity</li>
<li>any entity can be used alone or in concert with other entities</li>
<li>no entities are disjoint</li>
<li>anyone can define additional entities or subclasses </li>
<li>individual profiles using the model may recommend or limit attributes and relationships, but the model itself will not have restrictions</li>
</ul>
This implements a a theory of ontology development known as "minimum semantic commitment." In this theory, base vocabulary terms should be defined with as little semantics as possible, with semantics in this sense being the axiomatic semantics of RDF. An ontology whose terms have high semantic definition, such as the original FRBR, will provide fewer opportunities for re-use because uses must adhere to the tightly defined semantics in the original ontology. Less commitment in the base ontology means that there are greater opportunities for re-use; desired semantics can be defined in specific implementations through the creation of application profiles.<br />
<br />
Given this freedom, how would people choose to describe creative works? For example, here's one possible way to describe a work of art:<br />
<br />
work: <br />
title: Acrobats<br />
creator: Paul Klee<br />
genre: abstract art<br />
topic: acrobats<br />
date: 1914<br />
item:<br />
size: 9 x 9<br />
base material: paper<br />
material: watercolor, pastel, ink<br />
color: mixed<br />
signed: PKlee<br />
dated: 1914<br />
<br />
And here's a way to describe a museum store's inventory record for a print:<br />
<br />
work: <br />
title: Acrobats<br />
creator: Paul Klee<br />
genre: abstract art<br />
topic: acrobats<br />
date: 1914<br />
manifestation:<br />
description: 12-color archival inkjet print<br />
size: 24 x 36 inches<br />
price: $16.99<br />
<br />
There is also no reason why a non-creative product couldn't use the manifestation class (which is one of the reasons that I would prefer to call it "product," which would resonate better for these potential users):<br />
<br />
manifestation/product:<br />
description: dining chair<br />
dimensions: 26 x 23 x 21.5 inches<br />
weight: 21 pounds<br />
color: gray<br />
manufacturer: YEEFY<br />
price: $49.99<br />
<br />
Here is the sum total of what this core WEMI would look like, still using the FRBR terminology:<br />
<br />
<http://example.com/Work> rdf:type owl:Class ;<br />
rdfs:label "Work"@en ;<br />
rdfs:comment: "The creative work as abstraction."@en .<br />
<br />
<http://example.com/Expression> rdf:type owl:Class ;<br />
rdfs:label "Expression"@en ;<br />
rdfs:comment: "The creative work as it is expressed in a potentially perceivable form."@en .<br />
<br />
<http://example.com/Manifestation> rdf:type owl:Class ; rdfs:label "Manifestation"@en ;<br />
rdfs:comment: "The physical product that contains the creative work."@en .<br />
<br />
<http://example.com/Item> rdf:type owl:Class ;<br />
rdfs:label "Item"@en ;<br />
rdfs:comment: "An instance or individual copy of the creative work."@en .<br />
<br />
I can see communities like Dublin Core and schema.org as potential locations for these proposed classes because they represent general metadata communities, not just the GLAM world of IFLA. (I haven't approached them.) I'm open to hearing other ideas for hosting this, as well as comments on the ideas here. For it? Against it? Is there a downside?<br />
<br />
<hr />
* Examples of some "odd" references to FRBR for use in metadata for:<br />
<ul>
<li><a href="http://wittgensteinrepository.org/agora-alws/article/view/2675/3074">Wittgenstein's Tractatus</a> </li>
<li><a href="https://cloudfront.escholarship.org/dist/prd/content/qt3jf4g75m/qt3jf4g75m.pdf">live performances</a> </li>
<li><a href="https://jbiomedsem.biomedcentral.com/articles/10.1186/2041-1480-4-37">provenance of scientific data</a> </li>
<li><a href="https://dl.acm.org/citation.cfm?id=1568269O">legal documentation</a></li>
</ul>
<br />Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com2tag:blogger.com,1999:blog-3338174527262061848.post-32164497515111833852018-11-27T07:43:00.004-08:002019-01-10T11:54:29.747-08:00It's "academic"We all know that writing and publishing is of great concern to those whose work is in academia; the "publish or perish" burden haunts pre-tenure educators and grant-seeking researchers. Revelations that data had been falsified in published experimental results brings great condemnation from publishers and colleagues, and yet I have a feeling that underneath it all is more than an ounce of empathy from those who are fully aware of the forces that would lead one to put ones' thumbs on the scales for the purposes of winning the academic jousting match. It is only a slight exaggeration to compare these souls to the storied gladiators whose defeat meant summary execution. From all evidence, that is how many of them experience the contest to win the ivory tower - you climb until you fall.<br />
<br />
Research libraries and others deal in great part with the output of the academe. In many ways their practices reinforce the value judgments made on academic writing, such as having blanket orders for all works published by a list of academic presses. In spite of this, libraries have avoided making an overt statement of what is and what is not "academic." The "deciders" of academic writing are the publishers - primarily the publishers of peer-reviewed journals that decide what information does and does not become part of the record of academic achievement, but also those presses that issue scholarly monographs. Libraries are the consumers of these decisions but stop short of tagging works as "academic" or "scholarly."<br />
<br />
The pressure on academics has only increased in recent years, primarily because of the development of "impact factors." In 1955, Eugene Garfield introduced the idea that one could create a map of scientific publishing using an index of the writings cited by other works. (Science, 1955; 122 :108–11) Garfield was interested in improving science by linking works so that one could easily find supporting documents. However, over the years the purpose of citation has evolved from a convenient link to precedents into a measure of the worth of scholars themselves in the form of the "h-index" - the measure of how often a person (not a work) has been cited. The h-index is the "lifetime home runs" statistic of the academic world. One is valued for how many times one is cited, making citations the coin of the realm, not sales of works or even readership. No one in academia could or should be measured on the same scale as a non-academic writer when it comes to print runs, reviews, or movie deals. Imagine comparing the sales figures of <a href="https://global.oup.com/academic/product/poetic-autonomy-in-ancient-rome-9780199675630?q=poetic%20autonomy&lang=en&cc=us">"Poetic Autonomy in Ancient Rome"</a> with "The Da Vinci Code". So it matters in academia to carve out a world that is academic, and that isolates academic works such that one can do things like calculate an h-index value.<br />
<br />
This interest in all things academic has led to a number of metadata oddities that make me uncomfortable, however. There are metadata schemas that have an academic bent that translates to a need to assert the "scholarliness" of works being given a bibliographic description. There is also an emphasis on science in these bibliographic metadata, with less acknowledgement of the publishing patterns of the humanities. My problem isn't solely with the fact that they are doing this, but in particular with how they go about it.<br />
<br />
As an example, the metadata schema <a href="https://github.com/structureddynamics/Bibliographic-Ontology-BIBO/blob/master/bibo.owl">BIBO</a> clearly has an emphasis on <i>articles</i> as scholarly writing; notably, it has a publication type "academic article" but does not have a publication type for "academic book." This reflects the bias that new scientific discoveries are published as journal articles, and many scientists do not write book-length works at all. This slights the work of historians like Ann M. Blair whose book, <a href="https://www.amazon.com/Too-Much-Know-Scholarly-Information/dp/0300165390/">Too Much to Know</a>, has what I estimate to be about 1,450 "primary sources," ranging from manuscripts in Latin and German from the 1500's to modern works in a number of languages. It doesn't get much more academic than that.<br />
<br />
BIBO also has different metadata terms for "journal" and "magazine":<br />
<ul>
<li><span style="font-family: "courier new" , "courier" , monospace;"><span style="color: black;"><span class="wb-itemlink"><span class="wb-itemlink-label" dir="ltr" lang="en"><span class="searchmatch">bibo:journal "</span></span></span></span></span><span style="color: black;"><span class="wb-itemlink"><span class="wb-itemlink-label" dir="ltr" lang="en"><span class="searchmatch">A periodical of scholarly journal Articles."</span></span></span></span></li>
<li><span style="color: black;"><span class="wb-itemlink"><span class="wb-itemlink-label" dir="ltr" lang="en"><span class="searchmatch"><span style="font-family: "courier new" , "courier" , monospace;">bibo:magazine</span>"</span></span></span></span>A periodical of magazine Articles. A magazine is a publication that is
issued periodically, usually bound in a paper cover, and typically
contains essays, stories, poems, etc., by many writers, and often
photographs and drawings, frequently specializing in a particular
subject or area, as hobbies, news, or sports."</li>
</ul>
Something in that last bit on magazines smacks of "leisure time" while the journal clearly represents "serious work." It's also interesting that the description of magazine is quite long, describes the physical aspects ("usually bound in a paper cover"), and gives a good idea of the potential content. "Journal" is simply "scholarly journal articles." Aside from the circularity of the definitions (journal has journal articles, magazines have magazine articles), what this says is simply that a journal is a "not magazine."<br />
<br />
Apart from the snobbishness of the difference between these terms is the fact that one seeks in vain for a bright line between the two. There is, of course, the "I know it when I see it" test, and there is definitely some academic writing that you can pick out without hesitation. But is an opinion piece in the journal of a scientific society academic? How about a book review? How about a book review in the New York Review of Books (NYRB), where articles run to 2-5,000 words, are written by an academic in the field, and make use of the encyclopedic knowledge of the topic on the part of the reviewer? When <a href="http://ghsm.hms.harvard.edu/person/faculty/marcia-angell">Marcia Angell</a>, professor at the Harvard Medical School and former Editor in Chief of <i>The New England Journal of Medicine</i> writes for the NYRB, has she slipped her academic robes for something else? She seems to think so. On her professional web site she lists among her publications a (significantly long) letter to the editor (called a "comment" in academic journal-eze) of a science journal article about women in medicine but she does not include in her publication list the articles she has written for NYRB even though these probably make more use of her academic knowledge than the comment did. She is clearly making a decision about what is "academic" (i.e. career-related) and what is not. It seems that the dividing line is not the content of the writing but how her professional world esteems the publishing vehicle.<br />
<br />
<i></i>
Not to single out BIBO, I should mention other "culprits" in the tagging of scholarly works, such as <a href="http://wikidata.org/">WikiData</a>. Wikidata has:<br />
<div class="mw-search-result-heading">
<ul>
<li><span style="color: black;"><span class="wb-itemlink"><span class="wb-itemlink-label" dir="ltr" lang="en"><span class="searchmatch"><span style="font-family: "courier new" , "courier" , monospace;">academic journal article (Q18918145)</span> article published in an academic journal</span></span></span></span></li>
<li><span style="color: black;"><span class="wb-itemlink"><span class="wb-itemlink-label" dir="ltr" lang="en"><span class="searchmatch"><span style="font-family: "courier new" , "courier" , monospace;">academic writing (Q4119870)</span> academic writing and publishing is conducted in several sets of forms and genres</span></span></span></span></li>
<li><span style="color: black;"><span class="wb-itemlink"><span class="wb-itemlink-label" dir="ltr" lang="en"><span class="searchmatch"><span style="font-family: "courier new" , "courier" , monospace;">scholarly article (Q13442814)</span> article in an academic publication, usually peer reviewed</span></span></span></span></li>
<li><span style="color: black;"><span class="wb-itemlink"><span class="wb-itemlink-label" dir="ltr" lang="en"><span class="searchmatch"><span style="font-family: "courier new" , "courier" , monospace;">scholarly publication (Q591041) </span>scientific publications that report original empirical and theoretical work in the natural sciences</span></span></span></span></li>
</ul>
<span style="color: black;"><span class="wb-itemlink"><span class="wb-itemlink-label" dir="ltr" lang="en"><span class="searchmatch">There is so much wrong with each of these, from circular definitions to bias toward
science as the only scholarly pursuit (scholarly publication is a
"<i>scientific</i> publication" in the <i>"natural</i> sciences"). (I've already commented
on this in WikiData, sarcastically calling it a fine definition if you ignore the
various directions that science and scholarship have taken since the
mid-19th century.) What this reveals, however is that the publication and publisher defines whether the work is "scholarly." If any article in an academic publication is a scholarly article, then the comment by Dr. Angell is, by definition, scholarly, and the NYRB articles are not. Academia is, in fact, a circularly-defined world. </span></span></span></span></div>
<div class="mw-search-result-heading">
</div>
<div class="mw-search-result-heading">
<span style="color: black;"><span class="wb-itemlink"><span class="wb-itemlink-label" dir="ltr" lang="en"><span class="searchmatch">Giving one more example, </span></span></span></span><span style="color: black;"><span class="wb-itemlink"><span class="wb-itemlink-label" dir="ltr" lang="en"><span class="searchmatch"><a href="http://schema.org/">schema.org</a> has this:</span></span></span></span><br />
<ul>
<li><span style="color: black;"><span class="wb-itemlink"><span class="wb-itemlink-label" dir="ltr" lang="en"><span class="searchmatch"><span style="font-family: "courier new" , "courier" , monospace;">schema:ScholarlyArticle</span> (sub-class of Article) A scholarly article. </span></span></span></span></li>
</ul>
<span style="color: black;"><span class="wb-itemlink"><span class="wb-itemlink-label" dir="ltr" lang="en"><span class="searchmatch"></span></span></span></span><span style="color: black;"><span class="wb-itemlink"><span class="wb-itemlink-label" dir="ltr" lang="en"><span class="searchmatch"></span></span><span class="wb-itemlink-id"></span></span></span> </div>
Dig <i>that</i> definition! There are a few other types of article in schema, org, such as "newsArticle" and "techArticle" but it appears that all of those magazine articles would be simple "Article." <br />
<br />
Note that in real life publications call themselves whatever they wish. With a hint at how terms may have changed over time: <i>Ladies' Home Journal</i> calls itself a journal, and the periodical published by the American Association for the Advancement of Science, <i>Science</i>, gives
itself the domain sciencemag.org. "Science Magazine" just sounds right, doesn't it? <br />
<br />
It's not <i>wrong</i> for folks to characterize some publications and some writing as "academic" but any metadata term needs a clear definition, which these do not have. What this means is that people using these schemas are being asked to make a determination with very little guidance that would help them separate the scholarly or academic from... well, from the rest of publishing output. With the inevitable variation in categorization, you can be sure that in metadata coded with these schemas the separation between scholarly/academic and not scholarly/academic writing is probably not going to be useful because there will be little regularity of assignment between communities that are using this metadata.<br />
<br />
I admit that I picked on this particular metadata topic because I find the designation of "scholarly" or "academic" to be judgemental. If nothing else, when people judge they need some criteria for that judgement. What I would like to see is a clear definition that would help people decide what is and what is not "academic," and what the use cases are for why this typing of materials should be done. As with most categorizations, we can expect some differences in the decisions that will be made by catalogers and indexers working with these metadata schemas. A definition at least gives you something to discuss and to argue for. Right now we don't have that for scholarly/academic publications.<br />
<br />
And I am glad that libraries don't try to make this distinction. <br />
<br />
<br />Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com2tag:blogger.com,1999:blog-3338174527262061848.post-55813770341137565302018-08-14T07:10:00.000-07:002018-08-14T07:10:09.057-07:00Libraryland, We Have a Problem<div style="margin-bottom: 0in;">
<br /></div>
The first rule of every multi-step
program is to admit that you have a problem. I think it's time for us
librarians to take step one and admit that we do have a problem.
<br />
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
The particular problem that I have in
mind is the disconnect between library data and library systems in
relation to the category of metadata that libraries call "headings."
Headings are the strings in the library data that represent those
entities that would be entry points in a linear catalog like a card
catalog.
</div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
It pains me whenever I am an observer
to cataloger discussions on the proper formation of headings for
items that they are cataloging. The pain point is that I know that
the value of those headings is completely lost in the library systems
of today, and therefore there are countless hours of skilled
cataloger time that are being wasted.</div>
<div style="margin-bottom: 0in;">
<br /></div>
<h2 style="margin-bottom: 0in;">
The Heading</h2>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
Both book and card catalogs were
catalogs of headings. The catalog entry was a heading followed by
one or more bibliographic entries. Unfortunately, the headings serve
multiple purposes, which is generally not a good data practice but is due to the need for parsimony in library data when that data was analog, as in book and card catalogs.
</div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
<ul>
<li>A heading is a unique character string
for the "thing" – the person, the corporate body, the
family – essentially an identifier.</li>
</ul>
</div>
<blockquote class="tr_bq">
Tolkien,
J. R. R. (John Ronald Reuel), 1892-1973
</blockquote>
<ul><div align="LEFT" style="border: none; margin-bottom: 0in; orphans: 2; padding: 0in; widows: 2;">
</div>
</ul>
<div style="margin-bottom: 0in;">
<ul>
<li>It supports the selection of the entity
in the catalog from among the choices that are presented (although in
some cases the effectiveness of this is questionable)</li>
</ul>
</div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgIETgMES3jrhe9R9yxrlBIxpYF3JOHrGaeAGS29yFt5erY54KBKt7AUcVLvDw1xO4Ju26aFFaDJaA0WJd-Gz1fvHEjT4fTBJ-Zf3tOA0DxS-o8EzLw9vdkQw2YNaBlN1Jf_NwnjhDgudbH/s1600/fitzgeralde.jpeg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="364" data-original-width="269" height="320" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgIETgMES3jrhe9R9yxrlBIxpYF3JOHrGaeAGS29yFt5erY54KBKt7AUcVLvDw1xO4Ju26aFFaDJaA0WJd-Gz1fvHEjT4fTBJ-Zf3tOA0DxS-o8EzLw9vdkQw2YNaBlN1Jf_NwnjhDgudbH/s320/fitzgeralde.jpeg" width="236" /></a></div>
<br /></div>
<div style="margin-bottom: 0in;">
<ul>
<li>It is an access point, intended to be
the means of finding, within the catalog, those items held by the
library that meet the need of the user.
</li>
</ul>
</div>
<div style="margin-bottom: 0in;">
<ul>
<li>It provides the sort order for the
catalog entries (which is why you see inverted forms like "Tolkien,
J. R. R.")</li>
</ul>
<blockquote class="tr_bq">
<blockquote class="tr_bq">
United States. Department of State. Bureau for Refugee Programs<br />
United States. Department of State. Bureau of Administration<br />
United States. Department of State. Bureau of Administration and Security<br />
United States. Department of State. Bureau of African Affairs </blockquote>
</blockquote>
<ul>
</ul>
</div>
<ul></ul>
<div style="margin-bottom: 0in;">
<ul>
<li>That sort order, and those inverted
headings, also have a purpose of <i>collocation of entries by some
measure of "likeness</i>"</li>
</ul>
</div>
<blockquote class="tr_bq">
<blockquote class="tr_bq">
Tolkien,
J. R. R. (John Ronald Reuel), 1892-1973
<br />
<div style="margin-bottom: 0in;">
Tolkien Society</div>
<div style="margin-bottom: 0in;">
Tolkien Trust</div>
</blockquote>
</blockquote>
<div style="margin-bottom: 0in;">
The last three functions, providing a sort order, access, and collocation, have been lost in the online
catalog. The reasons for this are many, but the main explanation is
that keyword searching has replaced alphabetical browse as a way to
locate items in a library catalog.</div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
The upshot is that many hours are spent
during the cataloging process to formulate a left-anchored,
alphabetically order-able heading that has no functionality in
library catalogs other than as fodder for a context-less keyword
search.</div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
Once a keyword search is done the
resulting items are retrieved without any correlation to headings. It
may not even be clear which headings one would use to create a useful
order. The set of retrieved bibliographic resources from a single
keyword search may not provide a coherent knowledge graph. Here's an
illustration using the keyword "darwin":</div>
<div style="margin-bottom: 0in;">
<br /></div>
<blockquote class="tr_bq">
<div style="margin-bottom: 0in;">
<span style="font-size: small;">Gardiner, Anne.</span></div>
<div style="margin-bottom: 0in;">
<span style="font-size: small;">Melding of two spirits :
from the "Yiminga" of the Tiwi to the "Yiminga"
of Christianity / by Anne Gardiner ; art work by </span>
</div>
<div style="margin-bottom: 0in;">
<span style="font-size: small;"><b><u>Darwin</u> </b>: State Library of
the Northern Territory, 1993.</span></div>
<blockquote class="tr_bq">
<div style="margin-bottom: 0in;">
<span style="font-size: small;">Christianity--Australia--Northern
Territory.</span></div>
<div style="margin-bottom: 0in;">
<span style="font-size: small;">Tiwi (Australian
people)--Religion.</span></div>
<div style="margin-bottom: 0in;">
<span style="font-size: small;">Northern
Territory--Religion.</span></div>
</blockquote>
<div style="margin-bottom: 0in;">
<span style="font-size: small;"><br /></span></div>
<div style="margin-bottom: 0in;">
<span style="font-size: small;">Crabb, William <u><b>Darwin</b>.</u></span></div>
<div style="margin-bottom: 0in;">
<span style="font-size: small;">Lyrics of the golden west.
By W. D. Crabb.</span></div>
<div style="margin-bottom: 0in;">
<span style="font-size: small;">San Francisco, The
Whitaker & Ray company, 1898</span></div>
<blockquote class="tr_bq">
<div style="margin-bottom: 0in;">
<span style="font-size: small;">West (U.S.)--Poetry.</span></div>
</blockquote>
<div style="margin-bottom: 0in;">
<span style="font-size: small;"><br /></span></div>
<div style="margin-bottom: 0in;">
<span style="font-size: small;"><b><u>Darwin</u></b>, Charles,
1809-1882.</span></div>
<div style="margin-bottom: 0in;">
<span style="font-size: small;">Origin of species by means
of natural selection; or, The preservation of favored races in the
struggle for life and The descent of man and selection in relation to
sex, by Charles Darwin.</span></div>
<div style="margin-bottom: 0in;">
<span style="font-size: small;">New York, The Modern
library [1936]</span></div>
<blockquote class="tr_bq">
<div style="margin-bottom: 0in;">
<span style="font-size: small;">Evolution (Biology)</span></div>
<div style="margin-bottom: 0in;">
<span style="font-size: small;">Natural selection.</span></div>
<div style="margin-bottom: 0in;">
<span style="font-size: small;">Heredity.</span></div>
<div style="margin-bottom: 0in;">
<span style="font-size: small;">Human evolution.</span></div>
</blockquote>
<div style="margin-bottom: 0in;">
<span style="font-size: small;"><br /></span></div>
<div style="margin-bottom: 0in;">
<span style="font-size: small;">Bear, Greg, 1951-</span></div>
<div style="margin-bottom: 0in;">
<span style="font-size: small;"><u><b>Darwin</b>'s</u> radio / Greg
Bear.</span></div>
<div style="margin-bottom: 0in;">
<span style="font-size: small;">New York : Ballantine
Books, 2003.</span></div>
<blockquote class="tr_bq">
<div style="margin-bottom: 0in;">
<span style="font-size: small;">Women molecular
biologists--Fiction.</span></div>
<div style="margin-bottom: 0in;">
<span style="font-size: small;">DNA viruses--Fiction.</span></div>
</blockquote>
</blockquote>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
No matter what you would choose as a
heading on which to order these, it will not produce a sensible
collocation that would give users some context to understand the
meaning of this particular set of items – and that is because there
is no meaning to this set of items, just a coincidence of things
named "Darwin."<br />
<br />
<div style="margin-bottom: 0in;">
Headings that have been chosen to be
controlled strings should offer a more predictable user search
experience than free text searching, but headings do not necessarily
provide collocation. As an example, Wikipedia uses the names of its
pages as headings, and there are some rules (or at least preferred
practices) to make the headings sensible. A search in Wikipedia is a
left-to-right search on a heading string that is presented as a
drop-down list of a handful of headings that match the search string:</div>
<div style="margin-bottom: 0in;">
<br />
<br />
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEizchLpCvo5OHKGQqTieoKrqFo314K-OTr75j90jQksELRN-jhMO1PQdsGcvEQgYEDwP0ctJr9Ww02xAAvhkT8BLJHNrq7pCpMa3KJ3xqrJxRzegnUxjURNZvQ-IQ6ZQ5Wc0kXpD6ZtN8Za/s1600/darwinWPdropdown.jpg" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="483" data-original-width="491" height="314" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEizchLpCvo5OHKGQqTieoKrqFo314K-OTr75j90jQksELRN-jhMO1PQdsGcvEQgYEDwP0ctJr9Ww02xAAvhkT8BLJHNrq7pCpMa3KJ3xqrJxRzegnUxjURNZvQ-IQ6ZQ5Wc0kXpD6ZtN8Za/s320/darwinWPdropdown.jpg" width="320" /></a></div>
<br />
<div style="margin-bottom: 0in;">
<div class="separator" style="clear: both; text-align: center;">
<br /></div>
Included in the headings in the
drop-down are "see"-type terms that, when selected, take the
user directly to the entry for the preferred term. If there is no one
preferred term Wikipedia directs users to disambiguation pages to
help users select among similar headings:</div>
<div style="margin-bottom: 0in;">
<br /></div>
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgAoKRVfyKcB93uDBmOnbUOAzmynwVtQoy1H0eH-gb0jq7m8DS4GjV85UWoEdL3EUvmBVQj6_RssvQx7BjsMZaD8r1fLZBbucE17lIFLtxUFbClZZIRm4rrwbTm2rKMMoY8Pzw-JDCNWWfD/s1600/darwinWPdisam.jpeg" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="714" data-original-width="1099" height="258" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgAoKRVfyKcB93uDBmOnbUOAzmynwVtQoy1H0eH-gb0jq7m8DS4GjV85UWoEdL3EUvmBVQj6_RssvQx7BjsMZaD8r1fLZBbucE17lIFLtxUFbClZZIRm4rrwbTm2rKMMoY8Pzw-JDCNWWfD/s400/darwinWPdisam.jpeg" width="400" /></a>
</div>
<div style="margin-bottom: 0in;">
<br />
The Wikipedia
pages, however, only provide accidental collocation, not the more
comprehensive collocation that libraries aim to attain. That
library-designed collocation, however, is also the source of the inversion of
headings, making those strings unnatural and unintuitive for users. Although the library headings are
admirably rules based, they often use rules that will not be known to
many users of the catalog, such as the difference in name headings
with prepositions based on the language of the author. To search on
these names, one therefore needs to know the language of the author
and the rule that is applied to that language, something that I am
quite sure we can assume is not common knowledge among catalog users.<br />
<br /></div>
<blockquote class="tr_bq">
<div style="margin-bottom: 0in;">
De la Cruz, Melissa</div>
<div style="margin-bottom: 0in;">
Cervantes Saavedra, Miguel de</div>
</blockquote>
I may be the only patron of my small library branch that has known
to look for the mysteries by Icelandic author <span lang="en">Arnaldur
Indriðason under "A" not "I".</span></div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
<h2>
What Is To Be Done?</h2>
</div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
There isn't an easy (or perhaps not
even a hard) answer. As long as humans use words to describe their
queries we will have the problem that words and concepts, and words
and relationships between concepts, do not neatly coincide.
</div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
I see a few techniques that might be
used if we wish to save collocation by heading. One would be to allow
keyword searching but for the system to use that to suggest headings
that then can be used to view collocated works. Some systems do allow
users to retrieve headings by keyword, but headings, which are very
terse, are often not self-explanatory without the items they describe. A
browse of headings alone is much less helpful that the association of
the heading with the bibliographic data it describes. Remember that
headings were developed for the card catalog where they were printed
on the same card that carried the bibliographic description.</div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
Another possible area of investigation
would be to look to the classified catalog, a technique that has
existed alongside alphabetical catalogs for centuries. The <i>Decimal
Classification</i> of Dewey was a classified approach to knowledge with a
language-based index (his "Relativ Index") to the classes.
(It is odd that the current practice in US libraries is to have one
classification for items on shelves and an unrelated heading system
(LCSH) for subject access.)
</div>
<div style="margin-bottom: 0in;">
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgBENwiMSKcncVEHX5OR9lbubAIfs2jSUumwNOGDRl1dErGQxcb4YYyv0WRCyoFbxj_Zp_9wGlkd6ILu1dX5uwgv6NXh0krR9DvP81nh0kpeAK_KD2CCJI5OzfOBuEoiL_E5Bqew8GEI8LD/s1600/gregorianchantddc11.jpeg" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="120" data-original-width="393" height="97" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgBENwiMSKcncVEHX5OR9lbubAIfs2jSUumwNOGDRl1dErGQxcb4YYyv0WRCyoFbxj_Zp_9wGlkd6ILu1dX5uwgv6NXh0krR9DvP81nh0kpeAK_KD2CCJI5OzfOBuEoiL_E5Bqew8GEI8LD/s320/gregorianchantddc11.jpeg" width="320" /></a></div>
</div>
<div style="margin-bottom: 0in;">
The classification provides the
intellectual collocation that the headings themselves do not provide.
The difficulty with this is that the classification collocates
topically but, at least in its current form, does not collocate the
name headings in the catalog that identify people and organizations
as entities.</div>
<div style="margin-bottom: 0in;">
<h2>
Conclusion (sort of)</h2>
</div>
<div style="margin-bottom: 0in;">
Controlled headings as access points
for library catalogs could provide better service than keyword search
alone. How to make use of headings is a difficult question. The first
issue is how to exploit the precision of headings while still
allowing users to search on any terms that they have in mind. Keyword
search is, from the user's point of view, frictionless. They don't
have to think "what string would the library have used for
this?".
</div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
Collocation of items by topical
sameness or other relationships (e.g. "named for",
"subordinate to") is possibly the best service that
libraries could provide, although it is very hard to do this through
the mechanism of language strings. Dewey's original idea of a
classified order with a language-based index is still a good one,
although classifications are hard to maintain and hard to assign.
</div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
If challenged to state what I think the
library catalog should be, my answer would be that it should provide
a useful order that illustrates one or more intellectual contexts
that will help the user enter and navigate what the library has to
offer. Unfortunately I can't say today how we could do that. Could we
think about that together?</div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
<h2>
Readings</h2>
</div>
<div style="margin-bottom: 0in;">
Dewey, Melvil. <i>Decimal classification
and relativ index for libraries, clippings, notes, etc. </i>Edition 7.
Lake Placid Club, NY., Forest Press, 1911.
<a href="https://archive.org/details/decimalclassifi00dewegoog">https://archive.org/details/decimalclassifi00dewegoog</a><br />
<br />
Shera, Jesse H, Margaret E. Egan,
and Jeannette M. Lynn. <i>The Classified Catalog: Basic Principles and
Practices</i>. Chicago, Ill: American Library Association, 1956</div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
<br /></div>
<style type="text/css">P { margin-bottom: 0.08in; }A:link { }</style>Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com0tag:blogger.com,1999:blog-3338174527262061848.post-60511585267183791832018-08-06T08:34:00.003-07:002018-08-06T08:34:56.890-07:00FRBR as a Data Model<style type="text/css">
<!--
@page { margin: 0.79in }
P { margin-bottom: 0.08in }
-->
</style>
<br />
<div style="margin-bottom: 0in;">
<i>(I've been railing against FRBR since it was first introduced. It still confuses me some. I put out these ideas for discussion. If you disagree, please add your thoughts to this post.)</i></div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
I was recently speaking at a library
conference in OSLO where I went through my criticisms of our
cataloging models, and how they are not suited to the problems we
need to solve today. I had my usual strong criticisms of FRBR and the
IFLA LRM. However, when I finished speaking I was asked why I am so
critical of those models, which means that I did not explain myself
well. I am going to try again here, as clearly and succinctly as I
can.</div>
<div style="margin-bottom: 0in;">
<br /></div>
<h2 style="margin-bottom: 0in;">
Conflation of Conceptual Models with
Data Models</h2>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
FRBR's main impact was that it provided
a mental model of the bibliographic universe that reflects a
conceptual view of the elements of descriptive cataloging. You will
find nothing in FRBR that could not be found in standard library
cataloging of the 1990's, which is when the FRBR model was developed.
What FRBR adds to our understanding of bibliographic information is
that it gives names and definitions to key concepts that had been
implied but not fully articulated in library catalog data. If it had
stopped there we would have had an interesting mental model that
allows us to speak more precisely about catalogs and cataloging.</div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
Unfortunately, the use of diagrams that
appear to define actual data models and the listing of entities and
their attributes have led the library world down the wrong path, that
of reading FRBR as the definition of a physical data model.
Compounding this, the LRM goes down that path even further by
claiming to be a structural model of bibliographic data, which
implies that it is the structure for library catalog data. I maintain
that the FRBR conceptual model should not be assumed to also be a
model for bibliographic data in a machine-readable form. The main
reason for this has to do with the functionality that library
catalogs currently provide (and and what functions they may provide
in the future). This is especially true in relation to what FRBR
refers to as its Group 1 entities: work, expression, manifestation,
and item.</div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
The model defined in the FRBR document
presents an idealized view that does not reflect the functionality of
bibliographic data in library catalogs nor likely system design. This
is particularly obvious in the struggle to fit the reality of
aggregate works into the Group 1 "structure," but it is
true even for simple published resources. The remainder of this
document attempts to explain the differences between the ideal and
the real.</div>
<div style="margin-bottom: 0in;">
<br /></div>
<h2 style="margin-bottom: 0in;">
The Catalog vs the Universe</h2>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
One of the unspoken assumptions in the
FRBR document is that it poses its problems and solutions in the
context of the larger bibliographic universe, not in terms of a
library catalog. The idea of gathering all of the manifestations of
an expression and all of the expressions of a work is not shown as
contingent on the holdings of any particular library. Similarly,
bibliographic relationships are presented as having an existence
without addressing how those relationships would be handled when the
related works are not available in a data set. This may be due to the
fact that the FRBR working group was made up solely of
representatives of large research libraries whose individual catalogs
cover a significant swath of the bibliographic world. It may also
have arisen from the fact that the FRBR working group was formed to
address the exchange of data between national libraries, and thus was
intended as a universal model. Note that no systems designers were
involved in the development of FRBR to address issues that would come
up in catalogs of various extents or types.
</div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
The questions asked and answered by the
working group were therefore not of the nature of "how would
this work in a catalog?" and were more of the type "what is
nature of bibliographic data?". The latter is a perfectly
legitimate question for a study of the nature of bibliographic data,
but that study cannot be assumed to answer the first question.</div>
<div style="margin-bottom: 0in;">
<br /></div>
<h2 style="margin-bottom: 0in;">
Functionality</h2>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
Although the F in FRBR stands for
"functional" FRBR does little to address the functionality
of the library catalog. The user tasks find, identify, select and
obtain (and now explore, added in the LRM) are not explained in terms
of how the data aids those tasks; the FRBR document only lists which
data elements are essential to each task. Computer system design,
including the design of data structures, needs to go at least a step
further in its definition of functions, which means not only which
data elements are relevant, but the specific usage the data element
is put to in an actual machine interaction with the user and
services. A systems developer has to take into account precisely
what needs to be done with the FRBR entities in all of the system
functions, from input to search and display.
</div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
<i>(Note: I'm going to try to cover this better and to give examples in an upcoming post.)</i></div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
Analysis that is aimed at creating a
bibliographic data format for a library <i>catalog</i> would take
into account that providing user-facing information about work and
expression is context-dependent based on the holdings of the
individual library and on the needs of its users. It would also take
into account the optional use of work and expression information in
search and display, and possibly give alternate views to support
different choices in catalog creation and deployment. Essentially,
analysis for a catalog would take system functionality into account.</div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
There a lot of facts about the nature of
computer-based catalogs have to be acknowledged: that users are no
longer performing “find” in an alphabetical list of headings, but
are performing keyword searches; that collocation based on work-ness
is not a primary function of catalog displays; that a significant
proportion of a bibliographic database consists of items with a
single work-expression-manifestation grouping; and finally that there
is an inconsistent application of work and expression information in
today's data.
</div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
In spite of nearly forty years of using
library systems whose default search function is a single box in
which users are asked to input query terms that will be searched as
keywords taken from a combination of creator, title, and subject
fields in the bibliographic record, the LRM doubles down on the
status of textual headings as primary elements, aka: Nomen.
Unfortunately it doesn't address the search function in any
reasonable fashion, which is to say it doesn't give an indication of the role of
Nomen in the <i>find</i> function. In fact, here is the sum total of
what the LRM says about search:</div>
<div style="margin-bottom: 0in;">
<br /></div>
<blockquote class="tr_bq" style="margin-bottom: 0in;">
"<span style="font-size: small;">To
facilitate this task [find], the information system seeks to enable
effective searching by
offering appropriate search elements or functionality."</span></blockquote>
<br />
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
That's
all. As I said in my talk at Oslo, this is up there with the jokes
about bad corporate mission statements, like: "We endeavor to
enhance future value through intelligent paradigm implementation."
First, no information system <i>ineffective</i>
searching. Yet the phrase "effective searching" is
meaningless in itself; without a definition of what is <i>effective</i>
this is just a platitude. The same is true for "appropriate
search elements": no one would suggest that a system should use
<i>inappropriate</i>
search elements, but defining <i>appropriate</i> search
is not at all a simple task. In fact, I contend that one of the
primary problems with today's library systems is that we specifically
lack a definition of appropriate, effective search. This is rendered
especially difficult because the data that we enter into our library
systems is data that was designed for an entirely different
technology: the physical card catalog, organized as headings in
alphabetical order.</div>
<br />
<h2 style="margin-bottom: 0in;">
One Record to Rule Them All</h2>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
Our actual experience regarding
physical structures for bibliographic data should be sufficient proof
that there is not one single solution. Although libraries today are
consolidating around the MARC21 record format, primarily for economic
reasons, there have been numerous physical formats in use that mostly
adhere to the international standard of ISBD. In this same way, there
can be multiple physical formats that adhere to the conceptual model
expressed in the FRBR and LRM documents. We know this is the case by
looking at the current bibliographic data, which includes varieties
of MARC, ISBD, BIBFRAME, and others. Another option for surfacing
information about works in catalogs could follow what OCLC seems to
be developing, which is the creation of works through a clustering of
single-entity records. In that model, a work is a cluster of
expressions, and an expression is a cluster of manifestations. This
model has the advantage that it does not require the cataloger to
make decisions about work and expression statements before it is
known if the resource will be the progenitor of a bibliographic
family, or will stand alone. It also does not require the cataloger
to have knowledge of the bibliographic universe beyond their own
catalog.
</div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
The key element of all of these, and
countless other, solutions is that they can be faithful to the mental
model of FRBR while also being functional and efficient as systems.
We should also expect that the systems solutions to this problem
space will not stay the same over time, since technology is in
constant evolution.</div>
<div style="margin-bottom: 0in;">
<br /></div>
<h2 style="margin-bottom: 0in;">
Summary</h2>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
I have identified here two quite
fundamental areas where FRBR's analysis differs from the needs of
system development: 1) the difference between conceptual and physical
models and 2) the difference between the (theoretical) bibliographic
universe and the functional library catalog. Neither of these are a
criticism of FRBR as such, but they do serve as warnings about some
widely held assumptions in the library world today, which is that of
mistaking the FRBR entity model for a data and catalog design model.
This is evident in the outcry over the design of the BIBFRAME model
which uses a two-tiered bibliographic view and not the three-tiers of
FRBR. The irony of that complaint is that at the very same time as
those outcries, catalogers are using FRBR concepts (as embodied in
RDA) while cataloging into the one-tiered data model of MARC, which
includes all of the entities of FRBR in a single data record. While
cataloging into MARC records may not be the best version of
bibliographic data storage that we could come up with, we must
acknowledge that there are many possible technology solutions that
could allow the exercise of bibliographic control while making use of
the concepts addressed in FRBR/LRM. Those solutions must be based as
least as much on user needs in actual catalogs as on bibliographic
theory.</div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
As a theory, FRBR posits an ideal
bibliographic environment which is not the same as the one that is
embodied in any library catalog. The diagrams in the FRBR and LRM
documents show the structure of the mental model, but not library
catalog data. Because the FRBR document does not address
implementation of the model in a catalog, there is no test of how
such a model does or does not reflect actual system design. The
extrapolation from mental model to physical model is not provided in
FRBR or the LRM, as neither addresses system functions and design,
not even at a macro level.
</div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
I have to wonder if FRBR/LRM shouldn't
be considered a model for bibliography rather than library catalogs.
Bibliography was once a common art in the world of letters but that
has faded greatly over the last half century. Bibliography is not the
same as catalog creation, but one could argue that libraries and
librarians are the logical successors to the bibliographers of the
past, and that a “universal bibliography” created under the
auspices of libraries would provide an ideal context for the entries
in the library catalog. This could allow users to view the offerings
of a single library as a subset of a well-described world of
resources, most of which can be accessed in other libraries and
archives.</div>
<div style="margin-bottom: 0in;">
</div>
<div style="margin-bottom: 0in;">
<br /></div>
<div style="margin-bottom: 0in;">
<h3>
Bibliography</h3>
IFLA. <a href="https://www.ifla.org/files/assets/cataloguing/frbr/frbr_2008.pdf">Functional Requirements for Bibliographic Records</a>. 1998/2008<br />
IFLA.<a href="https://www.ifla.org/publications/node/11412"> Library Reference Model</a>. 2017</div>
<br />Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com3tag:blogger.com,1999:blog-3338174527262061848.post-16810336625038631812017-10-10T10:43:00.000-07:002017-10-10T10:43:00.030-07:00Google Books and Mein Kampf I hadn't look at Google Books in a while, or at least not carefully, so I was surprised to find that Google had added blurbs to most of the books. Even more surprising (although perhaps I should say "troubling") is that no source is given for the book blurbs. Some at least come from publisher sites, which means that they are promotional in nature. For example, here's a mildly promotional text about a literary work, from a <a href="http://www.chicagoreviewpress.com/raintree-county-products-9781556527104.php?page_id=21">literary publisher</a>:<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEih0TvqxvIJK0gaadTkA5ykjXJrDq3vyL3APpXyCBJ2sC0G9z8CfowYPYZgIYXj0E1EaIbcXhkWLjkyS984Eb-Cy_QRRNZNj4_hyphenhyphentfkr3UkXq61bMGVOlJY7topSpLhIS9NCvd_NsHzTj26/s1600/raintreeGoogle.jpeg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="395" data-original-width="582" height="217" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEih0TvqxvIJK0gaadTkA5ykjXJrDq3vyL3APpXyCBJ2sC0G9z8CfowYPYZgIYXj0E1EaIbcXhkWLjkyS984Eb-Cy_QRRNZNj4_hyphenhyphentfkr3UkXq61bMGVOlJY7topSpLhIS9NCvd_NsHzTj26/s320/raintreeGoogle.jpeg" width="320" /></a></div>
<br />
<br />
This gives a synopsis of the book, starting with:<br />
<br />
<blockquote class="tr_bq">
"Throughout a single day in 1892, John Shawnessy recalls the great moments of his life..." </blockquote>
<br />
It ends by letting the reader know that this was a bestseller when published in 1948, and calls it a "powerful novel."<br />
<br />
The blurb on a 1909 version of Darwin's The Origin of Species is mysterious because the book isn't a recent publication with an online site providing the text. I do not know where this description comes from, but because the entire thrust of this blurb is about the controversy of evolution versus the Bible (even though Darwin did not press this point himself) I'm guessing that the blurb post-dates this particular publication.<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgNt07UQfznz7tPmI96-o9mNsXsCwhLIZy1ZORzgpdLaexHumwJTpv_3gsx9TtAIljl2Js02XbjIk_t2CDnjOPCL-nwpbPkj-MIl2WK9PU8U31x1nX46MxuBZjWtywYC3OUIJsOeS2aL__x/s1600/DarwinGBooks.jpeg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="335" data-original-width="591" height="181" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgNt07UQfznz7tPmI96-o9mNsXsCwhLIZy1ZORzgpdLaexHumwJTpv_3gsx9TtAIljl2Js02XbjIk_t2CDnjOPCL-nwpbPkj-MIl2WK9PU8U31x1nX46MxuBZjWtywYC3OUIJsOeS2aL__x/s320/DarwinGBooks.jpeg" width="320" /></a></div>
<br />
<blockquote class="tr_bq">
"First published in 1859, this landmark book on evolutionary biology was not the first to deal with the subject, but it went on to become a sensation -- and a controversial one for many religious people who could not reconcile Darwin's science with their faith."</blockquote>
That's a reasonable view to take of Darwin's "landmark" book but it isn't what I would consider to be faithful to the full import of this tome.<br />
<br />
The blurb on Hitler's Mein Kampf is particularly troubling. If you look at different versions of the book you get both pro- and anti- Nazi sentiments, neither of which really belong on a site that claims to be a catalog of books. Also note that because each book entry has only one blurb, the tone changes considerably depending on which publication you happen to pick from the list.<br />
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj43wP1yd0kdI-f8qt_k4BFX2Q2X6_D7sNvyeg1VkYHrwcijmIxMdwHHfQVdxVa1aFkEUqn8Q3Ao89asbp0Vgo5EV4ApmyR3qYJhQF1mEKEz4h8-LpWnJjQ-hAT2eCsxISUSjJglYOpBc-s/s1600/MeinKampf2GBooks.jpeg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="313" data-original-width="698" height="143" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj43wP1yd0kdI-f8qt_k4BFX2Q2X6_D7sNvyeg1VkYHrwcijmIxMdwHHfQVdxVa1aFkEUqn8Q3Ao89asbp0Vgo5EV4ApmyR3qYJhQF1mEKEz4h8-LpWnJjQ-hAT2eCsxISUSjJglYOpBc-s/s320/MeinKampf2GBooks.jpeg" width="320" /></a></div>
<br />
<a href="https://books.google.com/books?id=TXcwKYcMFyoC&dq=mein+kampf&hl=en&sa=X&ved=0ahUKEwiHwM2zyubWAhXqyVQKHTTqCmMQ6AEIKDAA">First</a> on the list:<br />
<blockquote class="tr_bq">
"Settling Accounts became Mein Kampf, an unparalleled example of muddled economics and history, appalling bigotry, and an intense self-glorification of Adolf Hitler as the true founder and builder of the National Socialist movement. It was written in hate and it contained a blueprint for violent bloodshed."</blockquote>
<br />
<a href="https://books.google.com/books?id=px_joAEACAAJ&dq=mein+kampf&hl=en&sa=X&ved=0ahUKEwipoNjbu-bWAhXGy1QKHUcLBf4Q6AEILTAB">Second</a> on the list:<br />
<blockquote class="tr_bq">
"This book has set a path toward a much higher understanding of the self and of our magnificent destiny as living beings part of this Race on our planet. It shows us that we must not look at nature in terms of good or bad, but in an unfiltered manner. It describes what we must do if we want to survive as a people and as a Race."</blockquote>
That's horrifying. Note that both books are self-published, and the blurbs are the ones that I find on those books in Amazon, perhaps indicating that Google is sucking up books from the Amazon site. There is, or at least at one point there once was, a difference between Amazon and Google Books. Google, after all, scanned books in libraries and presented itself as a search engine for published texts; Amazon will sell you <a href="https://www.amazon.com/Donald-Trump-Classic-Tweets-Toilet/dp/B07258JCS8/ref=sr_1_3">Trump's tweets on toilet paper</a>. The only text on the Google Books page still claims that Google Books is about search: "Search the world's most comprehensive index of full-text books." <a href="https://books.google.com/googlebooks/library/partners.html">Libraries partnered</a> with Google with lofty promises of gains in scholarship:<br />
<blockquote class="tr_bq">
"Our participation in the Google Books Library Project will add significantly to the extensive digital resources the Libraries already deliver. It will enable the Libraries to make available more significant portions of its extraordinary archival and special collections to scholars and researchers worldwide in ways that will ultimately change the nature of scholarship." Jim Neal, Columbia University</blockquote>
I don't know how these folks now feel about having their texts intermingled with publications they would never buy and described by texts that may come from shady and unreliable sources.<br />
<br />
Even leaving aside the grossest aspects of the blurbs and Google's hypocrisy about its commercialization of its books project, adding blurbs to the book entries with no attribution and clearly not vetting the sources is extremely irresponsible. It's also very Google to create sloppy algorithms that illustrate their basic ignorance of the content their are working with -- in this case, the world's books.<br />
<br />Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com0tag:blogger.com,1999:blog-3338174527262061848.post-47615278005803766182017-08-08T12:54:00.000-07:002017-08-08T12:54:44.278-07:00On reading Library Journal, September, 1877Of the many advantages to retirement is the particular one of idle time. And I will say that as a librarian one could do no better than to spend some of that time communing with the history of the profession. The difficulty is that it is so rich, so familiar in many ways that it is hard to move through it quickly. Here is just a fraction of the potential value to be found in the September issue of volume two of Library Journal.* Admittedly this is a particularly interesting number because it reports on the second meeting of the American Library Association.<br />
<br />
For any student of library history it is especially interesting to encounter certain names as living, working members of the profession.<br />
<span id="goog_2012581578"></span><span id="goog_2012581579"></span><br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgppF38IN084sCyJfSfdkSaIPZjFIfiek7OGEu34SDqXRpS3-n1p_Pp-iRBymOEo4XatsT0KcZJrMiNqiKA4_5zeCCNN4BqZr71QcKy6oT3oQsl_GEh4G9ttJ78WNJHW21_INA8gLvv0KnI/s1600/LJ1877-1MDewey.jpeg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="59" data-original-width="256" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgppF38IN084sCyJfSfdkSaIPZjFIfiek7OGEu34SDqXRpS3-n1p_Pp-iRBymOEo4XatsT0KcZJrMiNqiKA4_5zeCCNN4BqZr71QcKy6oT3oQsl_GEh4G9ttJ78WNJHW21_INA8gLvv0KnI/s1600/LJ1877-1MDewey.jpeg" /></a></div>
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhmmrsqBGhlsw7B7fN8zOuOI179UoleRamWcZiNf1dCX7-Q-mO8us7tutlRLKezWcQPPRPivd_OP5ARaYmB4f1Gr2OZwHYhHNdL8eChgZZsc9j8p741UcR66J7_uRUw0GEMwG8RYF52ZbEL/s1600/LJ1877SeptCutter.jpeg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="102" data-original-width="390" height="83" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhmmrsqBGhlsw7B7fN8zOuOI179UoleRamWcZiNf1dCX7-Q-mO8us7tutlRLKezWcQPPRPivd_OP5ARaYmB4f1Gr2OZwHYhHNdL8eChgZZsc9j8p741UcR66J7_uRUw0GEMwG8RYF52ZbEL/s320/LJ1877SeptCutter.jpeg" width="320" /></a></div>
<br />
Other names reflect works that continued on, some until today, such as <a href="https://en.wikipedia.org/wiki/William_Frederick_Poole">Poole</a> and <a href="https://en.wikipedia.org/wiki/Richard_Rogers_Bowker">Bowker</a>, both names associated with long-running periodical indexes.<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEixEWqCJDp7MTJMB4FLPIcnsZ3Nm_OFsfcqCJSyMMlBUaO7r5_aS1QKOh111baPx3NUju-a3QOopLbVzmr5vPbN_vpR1KOye7i1wCnCkQ17fe3GNyxOK_5bEyNZxI6_WA0QQy4G8OE7C4nb/s1600/LJ1877Septp7Poole.jpeg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="97" data-original-width="633" height="49" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEixEWqCJDp7MTJMB4FLPIcnsZ3Nm_OFsfcqCJSyMMlBUaO7r5_aS1QKOh111baPx3NUju-a3QOopLbVzmr5vPbN_vpR1KOye7i1wCnCkQ17fe3GNyxOK_5bEyNZxI6_WA0QQy4G8OE7C4nb/s320/LJ1877Septp7Poole.jpeg" width="320" /></a></div>
<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj30Wmrj4I15zccsgU_HMWh4tFN-3OO5l7vdLffDFjMmFU8xwlEYAWBvEJR3s0YIo7ELHp08KQ9MDw5ORN_paJZpm0iDOPXTL2NqeaBxJKC1imjpU0oqBIpMRybIFY07r4K7T6i_6F9lVcW/s1600/LJ1877Septp60RRBowker.jpeg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="94" data-original-width="424" height="70" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj30Wmrj4I15zccsgU_HMWh4tFN-3OO5l7vdLffDFjMmFU8xwlEYAWBvEJR3s0YIo7ELHp08KQ9MDw5ORN_paJZpm0iDOPXTL2NqeaBxJKC1imjpU0oqBIpMRybIFY07r4K7T6i_6F9lVcW/s320/LJ1877Septp60RRBowker.jpeg" width="320" /></a></div>
What is particularly striking, though, is how many of the topics of today were already being discussed then, although obviously in a different context. The association was formed, at least in part, to help librarianship achieve the status of a profession. Discussed were the educating of the public on the role of libraries and librarians as well as providing education so that there could be a group of professionals to take the jobs that needed that professional knowledge. There was work to be done to convince state legislatures to support state and local libraries.<br />
<br />
One of the first acts of the American Library Association when it was founded in 1876 (as reported in the first issue of Library Journal) was to create a Committee on Cooperation. This is the seed for today's cooperative cataloging efforts as well as other forms of sharing among libraries. In 1877, undoubtedly encouraged by the participation of some members of the publishing community in ALA, there was hope that libraries and publishers would work together to create catalog entries for in-print works.<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg6QLgJZME1qVU8Q6dBlKI5ldDIEghRTrrHFF8X0VmhD74Vjoq-FEA6Nw9uYRxxRpZNlTeIwccuA4Mbj21E-riARV3GkCmNM19f4c07qhcnmuBEVg7utyNrcWlIPYKCkaTVD2f57lottSeZ/s1600/LJ1877Septp14Publisher.jpeg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="274" data-original-width="381" height="230" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg6QLgJZME1qVU8Q6dBlKI5ldDIEghRTrrHFF8X0VmhD74Vjoq-FEA6Nw9uYRxxRpZNlTeIwccuA4Mbj21E-riARV3GkCmNM19f4c07qhcnmuBEVg7utyNrcWlIPYKCkaTVD2f57lottSeZ/s320/LJ1877Septp14Publisher.jpeg" width="320" /></a></div>
This is one hope of the early participants that we are still working on, especially the desire that such catalog copy would be "uniform." Note that there were also discussions about having librarians contribute to the periodical indexes of R. R. Bowker and Poole, so the cooperation would flow in both directions.<br />
<br />
The physical organization of libraries also was of interest, and a detailed plan for a round (actually octagonal) library design was presented:<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjOteQCajAFOU44MFSKDZHBjPcV784_CcM7DNQx9MkEONlf7X6Wernyc6_1OOq1GFQlLXcqLS50EJ2CNFJdjs74jk_fAOAwSoFvgimKH3AYVhv3x4kLNMm-xark8LMmxplozUp-N1IL3lrs/s1600/LJSept1877p43ArticleTitle.jpeg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="76" data-original-width="519" height="46" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjOteQCajAFOU44MFSKDZHBjPcV784_CcM7DNQx9MkEONlf7X6Wernyc6_1OOq1GFQlLXcqLS50EJ2CNFJdjs74jk_fAOAwSoFvgimKH3AYVhv3x4kLNMm-xark8LMmxplozUp-N1IL3lrs/s320/LJSept1877p43ArticleTitle.jpeg" width="320" /></a></div>
His conclusion, however, shows a difference in our concepts of user privacy.<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhLhj4rvXa8vbpszT3WQNwM0jL9TuU-dO1Dfl3fK8DoP33JFQkPGlKMlMoxNHniD1NEo1Deb-u6cU6EjLm2DaIcYnpB4AFM64VLThAIVi0fMjHRHiQ93JhEruxOX6QrtBveQDId2Dp7VpW5/s1600/LJ1877Septp55Panopticon.jpeg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="144" data-original-width="379" height="121" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhLhj4rvXa8vbpszT3WQNwM0jL9TuU-dO1Dfl3fK8DoP33JFQkPGlKMlMoxNHniD1NEo1Deb-u6cU6EjLm2DaIcYnpB4AFM64VLThAIVi0fMjHRHiQ93JhEruxOX6QrtBveQDId2Dp7VpW5/s320/LJ1877Septp55Panopticon.jpeg" width="320" /></a></div>
Especially interesting to me are the discussions of library technology. I was unaware of some of the emerging technologies for reproduction such as the <a href="https://en.wikipedia.org/wiki/Mimeograph#Papyrograph">papyrograph</a> and the <a href="https://en.wikipedia.org/wiki/Electric_pen">electric pen</a>. In 1877, the big question, though, was whether to employ the new (but as yet un-perfected) technology of the typewriter in library practice.<br />
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjMHbYeAk8U2cQNJem9Rg46ysC_rfIjfBU46T25nMxyw2bZSTroJmgWoIGBz5XaTkAFjRdMwi_Eg0PJr2UXznTZ3lOzwqrKDjL0aayj6ePCkf3Atp4s6Hr2JaqDCBA1dWjRQQImTpVDciEV/s1600/LJ1877Septp34Typewriter.jpeg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="259" data-original-width="390" height="212" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjMHbYeAk8U2cQNJem9Rg46ysC_rfIjfBU46T25nMxyw2bZSTroJmgWoIGBz5XaTkAFjRdMwi_Eg0PJr2UXznTZ3lOzwqrKDjL0aayj6ePCkf3Atp4s6Hr2JaqDCBA1dWjRQQImTpVDciEV/s320/LJ1877Septp34Typewriter.jpeg" width="320" /></a></div>
<div class="separator" style="clear: both; text-align: left;">
<br /></div>
<div class="separator" style="clear: both; text-align: left;">
There was some poo-pooing of this new technology, but some members felt it may be reaching a state of usefulness.</div>
<div class="separator" style="clear: both; text-align: left;">
<br /></div>
<div class="separator" style="clear: both; text-align: center;">
<a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgnvQ67efTemTE1amOJes60B5c5VQ-FpdR1JO4XhXprJvj7yGTIugLaH72S9nvi5EfD41YBZ_OuE2ZV03IgAoVEP09b0q8zT1KH4E9Y8euyatWM61tYF9NYcvV-bfQRuqrmWj5U7uk37qyN/s1600/LJ1877Septp34Typewriter2.jpeg" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="295" data-original-width="387" height="243" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgnvQ67efTemTE1amOJes60B5c5VQ-FpdR1JO4XhXprJvj7yGTIugLaH72S9nvi5EfD41YBZ_OuE2ZV03IgAoVEP09b0q8zT1KH4E9Y8euyatWM61tYF9NYcvV-bfQRuqrmWj5U7uk37qyN/s320/LJ1877Septp34Typewriter2.jpeg" width="320" /></a></div>
<br />
"The President" in this case is Justin Winsor, Superintendent of the Boston Library, then president of the American Library Association. Substituting more modern technologies, I suspect we have all taken part in this discussion during our careers.<br />
<br />
Reading through the Journal evokes a strong sense of "le plus ça change..." but I admit that I find it all rather reassuring. The historical beginnings give me a sense of why we are who we are today, and what factors are behind some of our embedded thinking on topics.<br />
<br />
<hr />
* Many of the early volumes are available from <a href="https://catalog.hathitrust.org/Record/000494488?type%5B%5D=all&lookfor%5B%5D=library%20journal&ft=ft">HathiTrust</a>, if you have access. Although the texts themselves are public domain, these are Google-digitized books and are not available without a login. (Don't get me started!) If you do not have access to those, most of the volumes are available through the Internet Archive. Select "text" and search on "library journal". As someone without HathiTrust institutional access I have found most numbers in the range 1-39, but am missing (hint, hint): 5/1880; 8-9/1887-88; 17/1892; 19/1894; 28-30/1903-1905; 34-37;1909-1912. If I can complete the run I think it would be good to create a compressed archive of the whole and make that available via the Internet Archive to save others the time of acquiring them one at a time. If I can find the remainder that are pre-1923 I will add those in.<br />
<br />Karen Coylehttp://www.blogger.com/profile/02519757456533839003noreply@blogger.com3