To arrive at the results regarding the tone of coverage, PEJ employed computer coding software developed by Crimson Hexagon along with PEJ's traditional media research methods.

The technology for Crimson Hexagon is rooted in an algorithm created by Gary King, a professor at Harvard University's Institute for Quantitative Social Science. (Click here to view the study explaining the algorithm.)

According to Crimson Hexagon, the purpose of computer coding is to "take as data a potentially large set of text documents, of which a small subset is hand coded into an investigator-chosen set of mutually exclusive and exhaustive categories. As output, the methods give approximately unbiased and statistically consistent estimates of the proportion of all documents in each category."

This browseable 75-topic dynamic topic model of the Journal Science (1880-2002) is part of the on-line supplement to the submission "Modeling the Evolution of Science." This browser allows a user to visualize the dynamic topic model, and use the hidden topics that it has uncovered to guide an exploration of the original collection of documents.

RTextTools is a free, open source machine learning package for automatic text classification that makes it simple for both novice and advanced users to get started with supervised learning. The package includes nine algorithms for ensemble classification (svm, slda, boosting, bagging, random forests, glmnet, decision trees, neural networks, maximum entropy), comprehensive analytics, and thorough documentation.

Nice ranked list of SVM software.

We introduce supervised latent Dirichlet allocation (sLDA), a statistical model of labelled documents. The model accommodates a variety of response types. We derive an approximate maximum-likelihood procedure for parameter estimation, which relies on variational methods to handle intractable posterior expectations. Prediction problems motivate this research: we use the fitted model to predict response values for new documents. We test sLDA on two real-world problems: movie ratings predicted from reviews, and the political tone of amendments in the U.S. Senate based on the amendment text. We illustrate the benefits of sLDA versus modern regularized regression, as well as versus an unsupervised LDA analysis followed by a separate regression.

This is a C++ implementation of supervised latent Dirichlet allocation (sLDA) for classification.

Wikipedia's category hierarchy forms a graph. It's definitely cyclic (Category:Ethology belongs to Category:Behavior, which in turn belongs to Category:Ethology).

At any rate, did you know that "Chicago Stags coaches" are a subcategory of "Natural sciences"?

... any idea of what an instance could be?

Looking closely at http://id.loc.gov/vocabulary/iso639-1/fr for the first
time seriously (shame on me, can't even tell since when this URI has been
available) ...
I read that it is a *rdfs:subClassOf*
http://id.loc.gov/vocabulary/iso639-1/iso639-1_Language

Well, why isn't it an *instance* of this class?
I can see the rationale : there is not "one" French language, one can
imagine further subclasses such as Canadian French, Middle-Age French etc.
so French is a class of languages OK.
But are there any subclasses of French defined at id.loc.gov ?

And if it were the case, where do one stop the subclasses recursion and
introduce instances, if any? Is it turtles all the way down?

Let me show you which steps have to be taken to generate a high-quality text mining application, ready to be used to annotate and to categorize any kind of text or documents covering nearly any domain. With our approach of thesaurus based text mining your documents can also be linked to the world of linked (open) data; enrich your documents with data from the LOD cloud!

Michael Buckland's notes on Paul Otlet, with links to other Otlet resources.

"Paul Otlet (portrait) was born in Brussels, Belgium, in 1868. His monumental book Traité de documentation. (Brussels, 1934) was both central and symbolic in the development of information science - then called 'Documentation' - in the first half of this century. In addition, it reminds us of something that has been too widely forgotten: That this field did have a lively existence in the early decades of this century and a sophistication concerning theory and information technology that now commonly surprises people."

Lists of new and changed subject headings are posted to this Web site by the Policy and Standards Division as they are approved.

Survey of classificatory principles from bibliographic, philosophical, biological, psychological, and linguistic perspectives. Challenges to traditional principles from the cognitive sciences and their implementations for bibliographic classification.

This chapter studies the use of textual features based on systemic functional linguistics, for genre-based text categorization. We describe feature sets that represent different types of conjunctions and modal assessment, which together can partially indicate how different genres structure text and may prefer certain classes of attitudes towards propositions in the text. This enables analysis of large-scale rhetorical differences between genres by examining which features are important for classification. The specific domain we studied comprises scientific articles in historical and experimental sciences (paleontology and physical chemistry, respectively). We applied the SMO learning algorithm, which with our feature set achieved over 83% accuracy for classifying articles according to field, though no field-specific terms were used as features. The most highly-weighted features for each were consistent with hypothesized methodological differences between historical and experimental sciences, thus lending empirical evidence to the recent philosophical claim of multiple scientific methods.

If we treat each lettered heading in the Library of Congress Catalog as a single, long text, we can ask the computer to find similar genres based on word usage.

The Prediction API enables access to Google's machine learning algorithms to analyze your historic data and predict likely future outcomes.

Mahout's goal is to build scalable machine learning libraries.

This two-part article is a step-by-step guide for those wishing to create new taxonomies for their business unit, or client. It will outline the many different elements that make up a quality taxonomy and the pitfalls you should be aware of when starting a new project.

Browsable LOC classification.

Access to the most widely used cataloging documentation resources in an integrated, online system.

Browse and view authority headings for Subject, Name, Title and Name/Title combinations; and download authority records in MARC format.

A a comprehensive framework for recording descriptions of named geographic places, including the core elements of toponyms (and their history), spatial location (in various representations), and classification (according to referenced typing schemes), and

A set of terms for categories of geographic places; terms to indicate the nature of a place. It has been designed to be used with the Alexandria Digital Library (ADL) Gazetteer.

An RDF graph of the Library of Congress Classification Outline.

Distributed classification systems function at the intersection of individual choices and the shared linguistic/semantic norms of a social group (the folks in folksonomy).

The implementation of the Controlled Vocabulary takes great steps to help reduce inappropriate tagging, and to ease translation into any of the 12 languages now offered on iStock, by categorizing the search terms into a huge vocabulary tree.

Proposed W3C standard for labeling content as, e.g., mobile-friendly, kid-safe, trustworthy, dangerous, or otherwise certified to be something by somebody.

Using Library of Congress Authorities, you can browse and view authority headings for Subject, Name, Title and Name/Title combinations; and download authority records in MARC format for use in a local library system.

[Database] interfaces are modeled on existing genres and media, including the museum because of its archiving and classifying functions...

The MBA RSS Edited Feeds project is intended to create feeds from member blogs by subject, geography, both - or events.

FUTEF API provides a search API to explore and find Wikipedia content - including faceted categories.

A genre categorizer that lets users narrow down searches to particular genres like editorials, financial reports or scientific writing or group search results according to genre.

Faceted classification of BBC Creative Archive clips.

Jennifer and Kevin McCoy have exhaustively catalogued all the individual shots from all of the episodes of the 1970s television show Kung Fu and recompiled the shots according to genres.

Podcasters were not included in the new, popularized search and discovery mechanism where I believe most wanted to be; the directory is where the popular control lies now, especially when a directory is large and not open.

Sports video clip site combining taxonomic "channels" with fauxsonomic "tags."

Faceted tagclouds.

Orange is a component-based data mining software. It includes a range of preprocessing, modelling and data exploration techniques.

Reverend is a general purpose Bayesian classifier. Use the Reverend to quickly add Bayesian smarts to your app.

Articles that analyze tagging either through data, through situated comparisons or through philosophical hammering.

Understanding semantic relationships between concepts makes folksonomic tagging even more exciting.

This content-based image search and automatic learning-based linguistic indexing project was started in 1995.

"One thing that disturbs me about attacks on organized classification schemes (in general) is the ease in which decades of thinking and research are cast aside in favor of trendy, book-selling concepts of the moment."

Nice introduction to the SKOS RDF vocabulary for expressing concept schemes like thesauri and controlled vocabularies.

What would an information architect do with the wealth of information given by del.icio.us / flickr / technorati tags?

Dr. Bates has published widely in the areas of information system search strategy, user-centered design of information retrieval systems, and information seeking behavior.

Freetag is an easy tagging and folksonomy-enabled plugin for use with MySQL-PHP applications. It allows you to create tags on existing database schemas, and access and manage your tags through a robust API.

The value of genre theory for content engineering is, that it helps to look at the design problems from a different perspective, and to ask a different type of questions with a broader scope than prevailing usability engineering strategies raise.

Can assemble clips with common tags into automatic movies.

This is a collection of collaboratively edited taxonomies.