<?xml version="1.0" encoding="UTF-8"?>
 <rdf:RDF xmlns="http://purl.org/rss/1.0/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:cc="http://web.resource.org/cc/" xmlns:syn="http://purl.org/rss/1.0/modules/syndication/" xmlns:admin="http://webns.net/mvcb/">
  <channel rdf:about="http://pinboard.in">
    <title>Pinboard (cshalizi)</title>
    <link>https://pinboard.in/u:cshalizi/public/</link>
    <description>recent bookmarks from cshalizi</description>
    <items>
      <rdf:Seq>	<rdf:li rdf:resource="https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00415/107615/PAQ-65-Million-Probably-Asked-Questions-and-What"/>
	<rdf:li rdf:resource="https://dl.acm.org/doi/10.1145/321033.321035"/>
	<rdf:li rdf:resource="https://www.theverge.com/2024/12/5/24313222/chatgpt-pardon-biden-bush-esquire"/>
	<rdf:li rdf:resource="https://ceur-ws.org/Vol-3558/paper5712.pdf"/>
	<rdf:li rdf:resource="https://dl.acm.org/doi/abs/10.1145/3331184.3331340"/>
	<rdf:li rdf:resource="https://www.nytimes.com/2020/01/18/technology/clearview-privacy-facial-recognition.html"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1503.06410"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1908.07031"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1907.06902"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1902.02580"/>
	<rdf:li rdf:resource="http://press.princeton.edu/titles/10823.html"/>
	<rdf:li rdf:resource="http://www.nytimes.com/2016/05/19/opinion/the-real-bias-built-in-at-facebook.html?_r=0"/>
	<rdf:li rdf:resource="https://www.ideals.illinois.edu/handle/2142/1697"/>
	<rdf:li rdf:resource="http://geomblog.blogspot.com/2014/05/the-history-of-vector-space-model.html"/>
	<rdf:li rdf:resource="http://www.slate.com/articles/technology/bitwise/2014/03/stephen_wolfram_s_new_programming_language_can_he_make_the_world_computable.single.html"/>
	<rdf:li rdf:resource="http://www.cas.mcmaster.ca/~gk/courses/Sarah/Incremental%20Clustering.pdf"/>
	<rdf:li rdf:resource="http://mathbabe.org/2013/01/21/google-search-is-already-open-source/"/>
	<rdf:li rdf:resource="http://quomodocumque.wordpress.com/2013/01/16/graph-search-skepticism/"/>
	<rdf:li rdf:resource="http://www.mathstat.strath.ac.uk/downloads/publications/skapp.pdf"/>
	<rdf:li rdf:resource="http://jmlr.csail.mit.edu/papers/v9/lebanon08a.html"/>
	<rdf:li rdf:resource="http://www.sciencedirect.com/science/article/pii/S153204640300011X"/>
	<rdf:li rdf:resource="http://blog.pinboard.in/2011/10/the_fans_are_all_right/"/>
	<rdf:li rdf:resource="http://www.google.com/trends/correlate/draw"/>
	<rdf:li rdf:resource="http://www.cs.princeton.edu/~blei/papers/MimnoBlei2011.pdf"/>
	<rdf:li rdf:resource="http://www.pnas.org/content/107/41/17486.abstract?etoc"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1010.0499"/>
	<rdf:li rdf:resource="http://www.daveyp.com/blog/archives/1317"/>
	<rdf:li rdf:resource="http://pages.cs.wisc.edu/~jdavis/davisgoadrichcamera2.pdf"/>
	<rdf:li rdf:resource="http://www.wired.com/beyond_the_beyond/2010/03/world-brain-the-idea-of-a-permanent-world-encyclopedia/"/>
	<rdf:li rdf:resource="http://www.jair.org/papers/paper2934.html"/>
	<rdf:li rdf:resource="http://www.wired.com/magazine/2010/02/ff_google_algorithm/all/1"/>
	<rdf:li rdf:resource="http://www.wsdm-conference.org/2010/proceedings/docs/p221.pdf"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0910.2340"/>
	<rdf:li rdf:resource="http://icanhascheezburger.com/2009/09/08/funny-pictures-request-cause-its-stupid/"/>
	<rdf:li rdf:resource="http://bailando.sims.berkeley.edu/enron_email.html"/>
	<rdf:li rdf:resource="http://www.ldc.upenn.edu/Catalog/CatalogEntry.jsp?catalogId=LDC2008T19"/>
	<rdf:li rdf:resource="http://glinden.blogspot.com/2008/11/finding-task-boundaries-in-search-logs.html"/>
	<rdf:li rdf:resource="http://bayes.wordpress.com/2009/05/30/alpha-sprouts/"/>
	<rdf:li rdf:resource="http://www.cs.berkeley.edu/~brewer/papers/SearchDB.pdf"/>
	<rdf:li rdf:resource="http://www.zylstra.org/blog/archives/2009/05/wolframalpha_ge.html"/>
	<rdf:li rdf:resource="http://infolab.stanford.edu/~wangz/project/imsearch/review/JOUR/"/>
	<rdf:li rdf:resource="http://icanhascheezburger.com/2007/01/11/this-is-relevant-to-my-interests-2/"/>
	<rdf:li rdf:resource="http://www.semanticuniverse.com/blogs-i-was-positively-impressed-wolfram-alpha.html"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0807.2569"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0807.3755"/>
	<rdf:li rdf:resource="http://xstructure.inr.ac.ru/about.htm"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0807.1560"/>
	<rdf:li rdf:resource="http://www.nybooks.com/articles/21514"/>
	<rdf:li rdf:resource="http://www.uic.edu/htbin/cgiwrap/bin/ojs/index.php/fm/article/view/2008"/>
	<rdf:li rdf:resource="http://nlp.cs.nyu.edu/sekine/papers/coling06.pdf"/>
	<rdf:li rdf:resource="https://www.ipam.ucla.edu/schedule.aspx?pc=sews1"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0708.3601"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/0710.3972"/>
	<rdf:li rdf:resource="http://www.cs.brown.edu/~th/papers/Hofmann-UAI99.pdf"/>
	<rdf:li rdf:resource="http://itre.cis.upenn.edu/~myl/languagelog/archives/005086.html"/>
	<rdf:li rdf:resource="http://michaelnielsen.org/blog/?p=283"/>
	<rdf:li rdf:resource="http://research.google.com/pubs/papers.html"/>
	<rdf:li rdf:resource="http://www.google.com/technology/pigeonrank.html"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00415/107615/PAQ-65-Million-Probably-Asked-Questions-and-What">
    <title>PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them | Transactions of the Association for Computational Linguistics | MIT Press</title>
    <dc:date>2025-06-15T16:08:49+00:00</dc:date>
    <link>https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00415/107615/PAQ-65-Million-Probably-Asked-Questions-and-What</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Open-domain Question Answering models that directly leverage question-answer (QA) pairs, such as closed-book QA (CBQA) models and QA-pair retrievers, show promise in terms of speed and memory compared with conventional models which retrieve and read from text corpora. QA-pair retrievers also offer interpretable answers, a high degree of control, and are trivial to update at test time with new knowledge. However, these models fall short of the accuracy of retrieve-and-read systems, as substantially less knowledge is covered by the available QA-pairs relative to text corpora like Wikipedia. To facilitate improved QA-pair models, we introduce Probably Asked Questions (PAQ), a very large resource of 65M automatically generated QA-pairs. We introduce a new QA-pair retriever, RePAQ, to complement PAQ. We find that PAQ preempts and caches test questions, enabling RePAQ to match the accuracy of recent retrieve-and-read models, whilst being significantly faster. Using PAQ, we train CBQA models which outperform comparable baselines by 5%, but trail RePAQ by over 15%, indicating the effectiveness of explicit retrieval. RePAQ can be configured for size (under 500MB) or speed (over 1K questions per second) while retaining high accuracy. Lastly, we demonstrate RePAQ’s strength at selective QA, abstaining from answering when it is likely to be incorrect. This enables RePAQ to “back-off” to a more expensive state-of-the-art model, leading to a combined system which is both more accurate and 2x faster than the state-of-the-art model alone."]]></description>
<dc:subject>to:NB information_retrieval nearest_neighbors to_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:aea657f20142/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:nearest_neighbors"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://dl.acm.org/doi/10.1145/321033.321035">
    <title>On Relevance, Probabilistic Indexing and Information Retrieval | Journal of the ACM [1960]</title>
    <dc:date>2025-05-17T11:53:39+00:00</dc:date>
    <link>https://dl.acm.org/doi/10.1145/321033.321035</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper reports on a novel technique for literature indexing and searching in a mechanized library system. The notion of relevance is taken as the key concept in the theory of information retrieval and a comparative concept of relevance is explicated in terms of the theory of probability. The resulting technique called “Probabilistic Indexing,” allows a computing machine, given a request for information, to make a statistical inference and derive a number (called the “relevance number”) for each document, which is a measure of the probability that the document will satisfy the given request. The result of a search is an ordered list of those documents which satisfy the request ranked according to their probable relevance.
"The paper goes on to show that whereas in a conventional library system the cross-referencing (“see” and “see also”) is based solely on the “semantical closeness” between index terms, statistical measures of closeness between index terms can be defined and computed. Thus, given an arbitrary request consisting of one (or many) index term(s), a machine can elaborate on it to increase the probability of selecting relevant documents that would not otherwise have been selected.
"Finally, the paper suggests an interpretation of the whole library problem as one where the request is considered as a clue on the basis of which the library system makes a concatenated statistical inference in order to provide as an output an ordered list of those documents which most probably satisfy the information needs of the user."

--- 1960!]]></description>
<dc:subject>to_read information_retrieval relevance to_teach:data-mining via:mraginsky in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:0515f0733905/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:relevance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:mraginsky"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.theverge.com/2024/12/5/24313222/chatgpt-pardon-biden-bush-esquire">
    <title>Stop using generative AI as a search engine - The Verge</title>
    <dc:date>2024-12-06T13:56:06+00:00</dc:date>
    <link>https://www.theverge.com/2024/12/5/24313222/chatgpt-pardon-biden-bush-esquire</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[--- The "to_teach" tags are just the courses I'm gearing up for in the next few semesters; I suspect I will be giving _this_ lesson (and having it ignored) for many years to come.]]></description>
<dc:subject>large_language_models_(so_called) to_teach to_teach:data-mining to_teach:undergrad-ADA to_teach:statistics_of_inequality_and_discrimination information_retrieval have_read via:?</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:4dc951b569f7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:large_language_models_(so_called)"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:undergrad-ADA"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:statistics_of_inequality_and_discrimination"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:?"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://ceur-ws.org/Vol-3558/paper5712.pdf">
    <title>The Chatbot and the Canon: Poetry Memorization in LLMs</title>
    <dc:date>2024-03-30T18:28:28+00:00</dc:date>
    <link>https://ceur-ws.org/Vol-3558/paper5712.pdf</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Large language models are able to memorize and generate long passages of text from their pretraining data. Poetry is commonly available on the web and often fits within language model context sizes.  As LLMs continue to grow as a tool in literary analysis, the accessibility of poems will determine the effective canon. We assess whether we can prompt current language models to retrieve existing poems,
and what methods lead to the most successful retrieval. For the highest performing model, ChatGPT, we then evaluate which features of poets best predict memorization, as well as document changes over
time in ChatGPT’s ability and willingness to retrieve poetry."]]></description>
<dc:subject>information_retrieval poetry large_language_models_(so_called) via:rbuurma mimno.david natural_language_processing feral_library_catalogs in_NB have_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:eae98c989543/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:poetry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:large_language_models_(so_called)"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:rbuurma"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mimno.david"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:natural_language_processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:feral_library_catalogs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://dl.acm.org/doi/abs/10.1145/3331184.3331340">
    <title>Critically Examining the &quot;Neural Hype&quot; | Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval</title>
    <dc:date>2020-11-27T05:16:26+00:00</dc:date>
    <link>https://dl.acm.org/doi/abs/10.1145/3331184.3331340</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Is neural IR mostly hype? In a recent SIGIR Forum article, Lin expressed skepticism that neural ranking models were actually improving ad hoc retrieval effectiveness in limited data scenarios. He provided anecdotal evidence that authors of neural IR papers demonstrate "wins" by comparing against weak baselines. This paper provides a rigorous evaluation of those claims in two ways: First, we conducted a meta-analysis of papers that have reported experimental results on the TREC Robust04 test collection. We do not find evidence of an upward trend in effectiveness over time. In fact, the best reported results are from a decade ago and no recent neural approach comes close. Second, we applied five recent neural models to rerank the strong baselines that Lin used to make his arguments. A significant improvement was observed for one of the models, demonstrating additivity in gains. While there appears to be merit to neural IR approaches, at least some of the gains reported in the literature appear illusory."]]></description>
<dc:subject>to:NB information_retrieval neural_networks your_favorite_deep_neural_network_sucks</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:81c9d8582e62/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:neural_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:your_favorite_deep_neural_network_sucks"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.nytimes.com/2020/01/18/technology/clearview-privacy-facial-recognition.html">
    <title>The Secretive Company That Might End Privacy as We Know It - The New York Times</title>
    <dc:date>2020-01-19T18:03:44+00:00</dc:date>
    <link>https://www.nytimes.com/2020/01/18/technology/clearview-privacy-facial-recognition.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[The only thing which is beyond my undergrad class this semester is computing the feature vectors.  (And honestly I wonder how good that is.)

--- Because it's 2020: _Of course_ it's backed by a Giuliani crony who markets it to right-wing police officials.  _Of course_ Thiele is involved.  _Of course_ the founder appears dumbfounded when pressed on how it might be misused.  _Of course_ there's no independent verification or even a notion of false positives.]]></description>
<dc:subject>privacy information_retrieval image_processing pattern_recognition have_read to_teach:data-mining</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:85cde9298e7a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:privacy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:image_processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:pattern_recognition"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1503.06410">
    <title>[1503.06410] What the F-measure doesn't measure: Features, Flaws, Fallacies and Fixes</title>
    <dc:date>2019-09-13T13:17:32+00:00</dc:date>
    <link>https://arxiv.org/abs/1503.06410</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The F-measure or F-score is one of the most commonly used single number measures in Information Retrieval, Natural Language Processing and Machine Learning, but it is based on a mistake, and the flawed assumptions render it unsuitable for use in most contexts! Fortunately, there are better alternatives."

--- Not quite a crank, but definitely crank-y.]]></description>
<dc:subject>information_retrieval classifiers NOT_to_teach:data-mining my_initial_skeptical_coloration_became_on_examination_a_permanent_stain</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:55d719338a6d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:classifiers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:NOT_to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:my_initial_skeptical_coloration_became_on_examination_a_permanent_stain"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1908.07031">
    <title>[1908.07031] Evaluating Hierarchies through A Partially Observable Markov Decision Processes Methodology</title>
    <dc:date>2019-08-21T13:17:49+00:00</dc:date>
    <link>https://arxiv.org/abs/1908.07031</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Hierarchical clustering has been shown to be valuable in many scenarios, e.g. catalogues, biology research, image processing, and so on. Despite its usefulness to many situations, there is no agreed methodology on how to properly evaluate the hierarchies produced from different techniques, particularly in the case where ground-truth labels are unavailable. This motivates us to propose a framework for assessing the quality of hierarchical clustering allocations which covers the case of no ground-truth information. Such a quality measurement is useful, for example, to assess the hierarchical structures used by online retailer websites to display their product catalogues. Differently to all the previous measures and metrics, our framework tackles the evaluation from a decision theoretic perspective. We model the process as a bot searching stochastically for items in the hierarchy and establish a measure representing the degree to which the hierarchy supports this search. We employ the concept of Partially Observable Markov Decision Processes (POMDP) to model the uncertainty, the decision making, and the cognitive return for searchers in such a scenario. In this paper, we fully discuss the modeling details and demonstrate its application on some datasets."]]></description>
<dc:subject>to:NB clustering hierarchical_structure information_retrieval to_teach:data-mining</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ba57f7ffe636/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hierarchical_structure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1907.06902">
    <title>[1907.06902] Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches</title>
    <dc:date>2019-07-30T18:01:31+00:00</dc:date>
    <link>https://arxiv.org/abs/1907.06902</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Deep learning techniques have become the method of choice for researchers working on algorithmic aspects of recommender systems. With the strongly increased interest in machine learning in general, it has, as a result, become difficult to keep track of what represents the state-of-the-art at the moment, e.g., for top-n recommendation tasks. At the same time, several recent publications point out problems in today's research practice in applied machine learning, e.g., in terms of the reproducibility of the results or the choice of the baselines when proposing new models. In this work, we report the results of a systematic analysis of algorithmic proposals for top-n recommendation tasks. Specifically, we considered 18 algorithms that were presented at top-level research conferences in the last years. Only 7 of them could be reproduced with reasonable effort. For these methods, it however turned out that 6 of them can often be outperformed with comparably simple heuristic methods, e.g., based on nearest-neighbor or graph-based techniques. The remaining one clearly outperformed the baselines but did not consistently outperform a well-tuned non-neural linear ranking method. Overall, our work sheds light on a number of potential problems in today's machine learning scholarship and calls for improved scientific practices in this area. Source code of our experiments and full results are available at: this https URL."]]></description>
<dc:subject>information_retrieval your_favorite_deep_neural_network_sucks in_NB collaborative_filtering recommender_systems</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:19e4d07b80cb/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:your_favorite_deep_neural_network_sucks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:collaborative_filtering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:recommender_systems"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1902.02580">
    <title>[1902.02580] The few-get-richer: a surprising consequence of popularity-based rankings</title>
    <dc:date>2019-06-17T17:07:20+00:00</dc:date>
    <link>https://arxiv.org/abs/1902.02580</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Ranking algorithms play a crucial role in online platforms ranging from search engines to recommender systems. In this paper, we identify a surprising consequence of popularity-based rankings: the fewer the items reporting a given signal, the higher the share of the overall traffic they collectively attract. This few-get-richer effect emerges in settings where there are few distinct classes of items (e.g., left-leaning news sources versus right-leaning news sources), and items are ranked based on their popularity. We demonstrate analytically that the few-get-richer effect emerges when people tend to click on top-ranked items and have heterogeneous preferences for the classes of items. Using simulations, we analyze how the strength of the effect changes with assumptions about the setting and human behavior. We also test our predictions experimentally in an online experiment with human participants. Our findings have important implications to understand the spread of misinformation."]]></description>
<dc:subject>to:NB information_retrieval networked_life why_oh_why_cant_we_have_a_better_press_corps to_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:9c6e9ba58dac/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:networked_life"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:why_oh_why_cant_we_have_a_better_press_corps"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://press.princeton.edu/titles/10823.html">
    <title>Brinton, C. and Chiang, M.: The Power of Networks: Six Principles That Connect Our Lives. (eBook and Hardcover)</title>
    <dc:date>2016-12-29T17:37:58+00:00</dc:date>
    <link>http://press.princeton.edu/titles/10823.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Christopher Brinton and Mung Chiang offer an open and accessible pathway through the complexity of network design and deployment, and offer a readily understood, yet commendably deep, analysis of the technology and its operation. . . . A key strength of this study is its depth, for while the topics themselves are often apparently straightforward . . . the authors are admirably keen to drill down into the really important detail on which networks are founded, ensuring that we gain a real grasp of how the essential structures behave and operate. . . . In a world in which it is increasingly difficult to live without a profoundly intimate relationship with digital networks--whether you like it or not--the material presented in this text could usefully form a universal part of public education. . . . To describe this book as a course in digital citizenship would not be to overstate its importance."--John Gilbey, Times Higher Education]]></description>
<dc:subject>to:NB books:noted computer_networks computers collaborative_filtering data_mining information_retrieval networked_life</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:98b06d29f2c0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:books:noted"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:computer_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:computers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:collaborative_filtering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:data_mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:networked_life"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.nytimes.com/2016/05/19/opinion/the-real-bias-built-in-at-facebook.html?_r=0">
    <title>The Real Bias Built In at Facebook - The New York Times</title>
    <dc:date>2016-05-27T14:38:40+00:00</dc:date>
    <link>http://www.nytimes.com/2016/05/19/opinion/the-real-bias-built-in-at-facebook.html?_r=0</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>tufekci.zeynep networked_life data_mining social_media to_teach:data-mining information_retrieval</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:831e8aeb0187/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:tufekci.zeynep"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:networked_life"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:data_mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:social_media"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.ideals.illinois.edu/handle/2142/1697">
    <title>IDEALS @ Illinois: The Most Influential Paper Gerard Salton Never Wrote</title>
    <dc:date>2014-08-13T13:22:39+00:00</dc:date>
    <link>https://www.ideals.illinois.edu/handle/2142/1697</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Gerard Salton is often credited with developing the vector space model
 (VSM) for information retrieval (IR). Citations to Salton give the impression
 that the VSM must have been articulated as an IR model sometime between
 1970 and 1975. However, the VSM as it is understood today evolved over a
 longer time period than is usually acknowledged, and an articulation of the
 model and its assumptions did not appear in print until several years after
 those assumptions had been criticized and alternative models proposed. An
 often cited overview paper titled “A Vector Space Model for Information
 Retrieval” (alleged to have been published in 1975) does not exist, and
 citations to it represent a confusion of two 1975 articles, neither of which
 were overviews of the VSM as a model of information retrieval. Until the
 late 1970s, Salton did not present vector spaces as models of IR generally
 but rather as models of specifi c computations. Citations to the phantom
 paper refl ect an apparently widely held misconception that the operational
 features and explanatory devices now associated with the VSM must have
 been introduced at the same time it was fi rst proposed as an IR model."]]></description>
<dc:subject>information_retrieval data_mining history_of_technology historical_myths epidemiology_of_representations have_read to:blog in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:6b06d138bf22/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:data_mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:history_of_technology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:historical_myths"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:epidemiology_of_representations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:blog"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://geomblog.blogspot.com/2014/05/the-history-of-vector-space-model.html">
    <title>The Geomblog: The history of the vector space model</title>
    <dc:date>2014-08-13T13:21:19+00:00</dc:date>
    <link>http://geomblog.blogspot.com/2014/05/the-history-of-vector-space-model.html</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>information_retrieval data_mining to_teach:data-mining tracked_down_references to:blog</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:cf1d7701491b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:data_mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:tracked_down_references"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:blog"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.slate.com/articles/technology/bitwise/2014/03/stephen_wolfram_s_new_programming_language_can_he_make_the_world_computable.single.html">
    <title>Stephen Wolfram’s new programming language: Can he make the world computable?</title>
    <dc:date>2014-03-06T22:48:32+00:00</dc:date>
    <link>http://www.slate.com/articles/technology/bitwise/2014/03/stephen_wolfram_s_new_programming_language_can_he_make_the_world_computable.single.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[David Auerbach does the necessary.]]></description>
<dc:subject>information_retrieval wolfram.stephen auerbach.david the_mechanical_turk_of_the_semantic_web</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:830bcfef5dc2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:wolfram.stephen"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:auerbach.david"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:the_mechanical_turk_of_the_semantic_web"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cas.mcmaster.ca/~gk/courses/Sarah/Incremental%20Clustering.pdf">
    <title>INCREMENTAL CLUSTERING AND DYNAMIC INFORMATION RETRIEVAL</title>
    <dc:date>2013-04-04T18:06:05+00:00</dc:date>
    <link>http://www.cas.mcmaster.ca/~gk/courses/Sarah/Incremental%20Clustering.pdf</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Motivated by applications such as document and image classification in information retrieval, we consider the problem of clustering dynamic point sets in a metric space. We propose a model called incremental clustering which is based on a careful analysis of the requirements of the information retrieval application, and which should also be useful in other applications. The goal is to efficiently maintain clusters of small diameter as new points are inserted. We analyze several natural greedy algorithms and demonstrate that they perform poorly. We propose new deterministic and randomized incremental clustering algorithms which have a provably good performance, and which we believe should also perform well in practice. We complement our positive results with lower bounds on the performance of incremental algorithms. Finally, we consider the dual clustering problem where the clusters are of fixed diameter, and the goal is to minimize the number of clusters."]]></description>
<dc:subject>to:NB clustering online_learning computational_complexity machine_learning information_retrieval to_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ffcfdd7bc20f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:online_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:computational_complexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:machine_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://mathbabe.org/2013/01/21/google-search-is-already-open-source/">
    <title>Google search is already open source « mathbabe</title>
    <dc:date>2013-01-21T17:56:45+00:00</dc:date>
    <link>http://mathbabe.org/2013/01/21/google-search-is-already-open-source/</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["If we think there’s inherent racism in google searches, then we should run experiments like Nathan Newman recently did, examining the different ads that pop up when someone writes an email about buying a car, for example, with different names and in different zip codes. We should organize to change our zip codes, our personas (which would mean deliberately creating personas and gmail logins, etc.), and our search terms, and see how the Google search results change as our inputs change.
"After all, I don’t know what’s in the code base but I’m pretty sure there’s no sub-routine that’s called “add_racism_to_search”; instead, it’s a complicated Rube-Goldberg machine that should be judged by its outputs, in a statistical way, rather than expected to prescriptively describe how it treats things on a case-by-case basis.
"Another thing: I don’t think there are bad intentions on the part of the modelers, but that doesn’t mean there aren’t bad consequences – the model is too complicated for anyone to anticipate exactly how it acts unless they perform experiments to test them. In the meantime, until people undertand that, we need to distinguish between the intentions and the results."]]></description>
<dc:subject>information_retrieval the_singularity_has_happened unintended_consequences to_teach:data-mining algorithmic_fairness</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ce1be7308dae/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:the_singularity_has_happened"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:unintended_consequences"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:algorithmic_fairness"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://quomodocumque.wordpress.com/2013/01/16/graph-search-skepticism/">
    <title>Graph search skepticism | Quomodocumque</title>
    <dc:date>2013-01-17T03:48:51+00:00</dc:date>
    <link>http://quomodocumque.wordpress.com/2013/01/16/graph-search-skepticism/</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["You know how they tell you, if you’re confused about something in class and you want to know the answer, you should raise your hand and ask, because probably other people have the same question?  That’s the Google principle, except they take it one step further; if you need an answer, not only do other people have the same question, but one such person has already found the answer and put it on the web.  Google can’t tell you which states that entered the Union after 1875 have public universities with animals as their mascots, or which Congressional district ranks 10th by percentage of area covered by water, which is the kind of thing Wolfram Alpha is ace at; but that’s because no one has ever asked those questions, and no one ever will."

--- I am not 100% sure that this is an _accurate_ statement of the situation, but it's a _well-put_ one.]]></description>
<dc:subject>search_engines information_retrieval artificial_intelligence semantics_from_syntax ellenberg.jordan to_teach:data-mining</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:1b1e1cc77aed/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:search_engines"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:artificial_intelligence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:semantics_from_syntax"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ellenberg.jordan"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.mathstat.strath.ac.uk/downloads/publications/skapp.pdf">
    <title>THE SINKHORN-KNOPP ALGORITHM: CONVERGENCE AND APPLICATIONS</title>
    <dc:date>2013-01-10T22:47:15+00:00</dc:date>
    <link>http://www.mathstat.strath.ac.uk/downloads/publications/skapp.pdf</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["As long as a square nonnegative matrix A contains sufficient nonzero elements, then the Sinkhorn-Knopp algorithm can be used to balance the matrix, that is, to find a diagonal scaling of A that is doubly stochastic. It is known that the convergence is linear and an upper bound has been given for the rate of convergence for positive matrices. In this paper we give an explicit expression for the rate of convergence for fully indecomposable matrices.
"We describe how balancing algorithms can be used to give a measure of web page significance. We compare the measure with some well known alternatives, including PageRank. We show that with an ap- propriate modification, the Sinkhorn-Knopp algorithm is a natural candidate for computing the measure on enormous data sets."]]></description>
<dc:subject>to:NB numerical_analysis matrices information_retrieval markov_models spectral_clustering</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ac7c95214da8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:numerical_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:matrices"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:spectral_clustering"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://jmlr.csail.mit.edu/papers/v9/lebanon08a.html">
    <title>Non-Parametric Modeling of Partially Ranked Data</title>
    <dc:date>2012-02-05T18:54:04+00:00</dc:date>
    <link>http://jmlr.csail.mit.edu/papers/v9/lebanon08a.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Statistical models on full and partial rankings of n items are often of limited practical use for large n due to computational consideration. We explore the use of non-parametric models for partially ranked data and derive computationally efficient procedures for their use for large n. The derivations are largely possible through combinatorial and algebraic manipulations based on the lattice of partial rankings. A bias-variance analysis and an experimental study demonstrate the applicability of the proposed method."]]></description>
<dc:subject>to:NB statistics machine_learning categorical_data ordinal_data information_retrieval nonparametrics lebanon.guy</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:44482224cc87/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:machine_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:categorical_data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ordinal_data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:nonparametrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:lebanon.guy"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.sciencedirect.com/science/article/pii/S153204640300011X">
    <title>The structure of science information (Harris, 2002)</title>
    <dc:date>2011-12-15T19:41:16+00:00</dc:date>
    <link>http://www.sciencedirect.com/science/article/pii/S153204640300011X</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The organization of information within science can be investigated in a principled way through analysis of science language. The restricted use of language in science enables description of the informational structure of science and of particular subfields, with strong similarities to structures in mathematics and programming languages. This result rests on decades of research into the relation between form and content in language, based on an information-theoretic approach to the structure of information. Examples are provided from immunology and the social sciences. Practical applications include storage of science information in databases, indexing the literature, and identification and resolution of controversy."]]></description>
<dc:subject>to:NB linguistics text_mining natural_language_processing harris.zellig information_retrieval</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:d09408de20f1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:linguistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:text_mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:natural_language_processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:harris.zellig"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://blog.pinboard.in/2011/10/the_fans_are_all_right/">
    <title>The Fans Are All Right (Pinboard Blog)</title>
    <dc:date>2011-10-07T02:07:40+00:00</dc:date>
    <link>http://blog.pinboard.in/2011/10/the_fans_are_all_right/</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["I learned a lot about fandom couple of years ago in conversations with my friend Britta, who was working at the time as community manager for Delicious. She taught me that fans were among the heaviest users of the bookmarking site, and had constructed an edifice of incredibly elaborate tagging conventions, plugins, and scripts to organize their output along a bewildering number of dimensions. If you wanted to read a 3000 word fic where Picard forces Gandalf into sexual bondage, and it seems unconsensual but secretly both want it, and it's R-explicit but not NC-17 explicit, all you had to do was search along the appropriate combination of tags (and if you couldn't find it, someone would probably write it for you). By 2008 a whole suite of theoretical ideas about folksonomy, crowdsourcing, faceted infomation retrieval, collaborative editing and emergent ontology had been implemented by a bunch of friendly people so that they could read about Kirk drilling Spock."  --- See also the very last link.]]></description>
<dc:subject>fandom social_life_of_the_mind social_media information_retrieval tagging pinboard via:arsyed to_teach:data-mining ok_maybe_not_really_to_teach delicious.com</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:aa9a7bc950f1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:fandom"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:social_life_of_the_mind"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:social_media"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:tagging"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:pinboard"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arsyed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ok_maybe_not_really_to_teach"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:delicious.com"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.google.com/trends/correlate/draw">
    <title>Draw - Google Correlate</title>
    <dc:date>2011-10-01T18:22:20+00:00</dc:date>
    <link>http://www.google.com/trends/correlate/draw</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[So cool: draw a curve free-hand, get the keywords whose time series correlate best with it.  I can't go below a correlation of 0.70.
]]></description>
<dc:subject>google information_retrieval spurious_correlations to_teach:undergrad-ADA to_teach:data-mining to:blog via:vqv rademacher_complexity</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:3b1bc129dfd9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:google"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:spurious_correlations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:undergrad-ADA"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:blog"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:vqv"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:rademacher_complexity"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cs.princeton.edu/~blei/papers/MimnoBlei2011.pdf">
    <title>Bayesian Checking for Topic Models</title>
    <dc:date>2011-07-14T13:52:51+00:00</dc:date>
    <link>http://www.cs.princeton.edu/~blei/papers/MimnoBlei2011.pdf</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Real document collections do not fit the inde- pendence assumptions asserted by most statistical topic models, but how badly do they violate them? We present a Bayesian method for measuring how well a topic model fits a corpus. Our approach is based on posterior predictive checking, a method for diagnosing Bayesian models in user-defined ways. Our method can identify where a topic model fits the data, where it falls short, and in which directions it might be improved."
]]></description>
<dc:subject>topic_models blei.david via:ariddell statistics machine_learning information_retrieval clustering have_read in_NB model_checking</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:8153af01dbf6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:topic_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:blei.david"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:ariddell"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:machine_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:model_checking"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.pnas.org/content/107/41/17486.abstract?etoc">
    <title>Predicting consumer behavior with Web search — PNAS</title>
    <dc:date>2010-10-15T23:51:19+00:00</dc:date>
    <link>http://www.pnas.org/content/107/41/17486.abstract?etoc</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[What search can and cannot predict.  They mention, but I think could have stressed even more, that the search data is generated _automatically_ as a by-product of now-ordinary social life, rather than a deliberate construction on the part of public or private data-collecting agencies, so it is very, very, very cheap.
]]></description>
<dc:subject>internet data_mining to_teach:data-mining kith_and_kin watts.duncan hofman.jake sociology information_retrieval networked_life have_read</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:6133ea6f4d4e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:internet"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:data_mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:watts.duncan"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hofman.jake"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:sociology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:networked_life"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1010.0499">
    <title>[1010.0499] Statistical analysis of $k$-nearest neighbor collaborative recommendation</title>
    <dc:date>2010-10-05T13:22:32+00:00</dc:date>
    <link>http://arxiv.org/abs/1010.0499</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Collaborative recommendation is an information-filtering technique that attempts to present information items that are likely of interest to an Internet user. Traditionally, collaborative systems deal with situations with two types of variables, users and items. In its most common form, the problem is framed as trying to estimate ratings for items that have not yet been consumed by a user. Despite wide-ranging literature, little is known about the statistical properties of recommendation systems. In fact, no clear probabilistic model even exists which would allow us to precisely describe the mathematical forces driving collaborative filtering. ... [We] set out a general sequential stochastic model for collaborative recommendation. ... in-depth analysis of the so-called cosine-type nearest neighbor ,,, method .... asymptotic performance as the number of users grows. We establish consistency ...  under mild assumptions... Rates of convergence and examples ..."
]]></description>
<dc:subject>collaborative_filtering information_retrieval stochastic_models nearest_neighbors to_teach:data-mining recommender_systems in_NB</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:f1b74089f8c5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:collaborative_filtering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:nearest_neighbors"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:recommender_systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.daveyp.com/blog/archives/1317">
    <title>ILI 2009 Presentation – &quot;Self-plagiarism is style&quot;</title>
    <dc:date>2010-06-28T17:46:51+00:00</dc:date>
    <link>http://www.daveyp.com/blog/archives/1317</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Cool effects achieved by applying basic data mining to libraries.  To be used as teaching fodder, but honestly I should also find the time to suggest it to our librarians.
]]></description>
<dc:subject>libraries data_mining information_retrieval collaborative_filtering via:magistra_et_mater to_teach:data-mining</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:3019c205f5bd/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:libraries"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:data_mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:collaborative_filtering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:magistra_et_mater"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://pages.cs.wisc.edu/~jdavis/davisgoadrichcamera2.pdf">
    <title>The Relationship Between Precision-Recall and ROC Curves</title>
    <dc:date>2010-04-30T02:25:43+00:00</dc:date>
    <link>http://pages.cs.wisc.edu/~jdavis/davisgoadrichcamera2.pdf</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>precision-recall hypothesis_testing information_retrieval machine_learning to_teach:data-mining</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:1dab546f5162/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:precision-recall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hypothesis_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:machine_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.wired.com/beyond_the_beyond/2010/03/world-brain-the-idea-of-a-permanent-world-encyclopedia/">
    <title>World Brain: the Idea of a Permanent World Encyclopedia | Beyond The Beyond</title>
    <dc:date>2010-03-04T22:46:23+00:00</dc:date>
    <link>http://www.wired.com/beyond_the_beyond/2010/03/world-brain-the-idea-of-a-permanent-world-encyclopedia/</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[H. G. Wells prophesies, well, something like us, in 1937; with commentary by Bruce Sterling.  Can't recall if Bush mentioned this.
]]></description>
<dc:subject>early_visions_of_network_society encyclopedias sterling.bruce information_retrieval the_present_before_it_was_widely_distributed to:blog wells.h.g.</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:bc15204eba7d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:early_visions_of_network_society"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:encyclopedias"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:sterling.bruce"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:the_present_before_it_was_widely_distributed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:blog"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:wells.h.g."/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.jair.org/papers/paper2934.html">
    <title>P. D. Turney and P. Pantel (2010) From Frequency to Meaning: Vector Space Models of Semantics</title>
    <dc:date>2010-02-28T23:27:37+00:00</dc:date>
    <link>http://www.jair.org/papers/paper2934.html</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>to_teach:data-mining information_retrieval latent_semantic_analysis</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:06928f59f95f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:latent_semantic_analysis"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.wired.com/magazine/2010/02/ff_google_algorithm/all/1">
    <title>Exclusive: How Google’s Algorithm Rules the Web | Magazine</title>
    <dc:date>2010-02-23T18:02:18+00:00</dc:date>
    <link>http://www.wired.com/magazine/2010/02/ff_google_algorithm/all/1</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>to_teach:data-mining information_retrieval search_engines google via:klk</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:a8ac820f4c98/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:search_engines"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:google"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:klk"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.wsdm-conference.org/2010/proceedings/docs/p221.pdf">
    <title>Beyond DCG: User Behavior as a Predictor of a Successful Search</title>
    <dc:date>2010-02-14T22:53:00+00:00</dc:date>
    <link>http://www.wsdm-conference.org/2010/proceedings/docs/p221.pdf</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Yay Kristina!  (Not sure I could actually teach this in 350.)
]]></description>
<dc:subject>search_engines markov_models data_mining information_retrieval to_teach:data-mining kith_and_kin klinkner.kristina</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:8f76159d9033/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:search_engines"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:data_mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:klinkner.kristina"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0910.2340">
    <title>[0910.2340] A Stochastic Model for Collaborative Recommendation</title>
    <dc:date>2009-10-21T02:00:47+00:00</dc:date>
    <link>http://arxiv.org/abs/0910.2340</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Collaborative recommendation is an information-filtering technique that attempts to present ,,, movies, music, books, news, images, Web pages, etc. that are likely of interest to  [users]. ... In its most common form, the problem is framed as trying to estimate ratings for items that have not yet been consumed by a user. Despite wide-ranging literature, little is known about the statistical properties of recommendation systems. In fact, no clear probabilistic model even exists allowing us to precisely describe the mathematical forces driving collaborative filtering. To provide an initial contribution to this, we propose to set out a general sequential stochastic model for collaborative recommendation and analyze its asymptotic performance as the number of users grows.... analysis of the so-called cosine-type nearest neighbor collaborative method .... consistency of the procedure under mild assumptions on the model. Rates of convergence and examples..."
]]></description>
<dc:subject>collaborative_filtering information_retrieval data_mining to_teach:data-mining in_NB recommender_systems</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ceff3a521db0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:collaborative_filtering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:data_mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:recommender_systems"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://icanhascheezburger.com/2009/09/08/funny-pictures-request-cause-its-stupid/">
    <title>Firefox rejects your « Lolcats ‘n’ Funny Pictures of Cats – I Can Has Cheezburger?</title>
    <dc:date>2009-09-09T03:24:25+00:00</dc:date>
    <link>http://icanhascheezburger.com/2009/09/08/funny-pictures-request-cause-its-stupid/</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Need to work this in as an easter-egg in the code.
]]></description>
<dc:subject>lolcats lolfoxes information_retrieval to_teach:data-mining</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:a03f659ea1d9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:lolcats"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:lolfoxes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://bailando.sims.berkeley.edu/enron_email.html">
    <title>UC Berkeley Enron Email Analysis</title>
    <dc:date>2009-08-21T19:23:51+00:00</dc:date>
    <link>http://bailando.sims.berkeley.edu/enron_email.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[With hand-labeled categories.
]]></description>
<dc:subject>enron email text_mining information_retrieval fraud to_teach:data-mining</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:460198ae5990/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:enron"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:email"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:text_mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:fraud"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.ldc.upenn.edu/Catalog/CatalogEntry.jsp?catalogId=LDC2008T19">
    <title>LDC Catalog: New York Times Annotated Corpus</title>
    <dc:date>2009-08-21T15:25:53+00:00</dc:date>
    <link>http://www.ldc.upenn.edu/Catalog/CatalogEntry.jsp?catalogId=LDC2008T19</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Sounds like it would be perfect for 350.  Now how the **** do I get access?
]]></description>
<dc:subject>information_retrieval text_mining newspapers data_sets to_teach:data-mining via:myl</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:90c5e1d1e9ce/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:text_mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:newspapers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:data_sets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:myl"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://glinden.blogspot.com/2008/11/finding-task-boundaries-in-search-logs.html">
    <title>Geeking with Greg: Finding task boundaries in search logs</title>
    <dc:date>2009-08-15T01:37:58+00:00</dc:date>
    <link>http://glinden.blogspot.com/2008/11/finding-task-boundaries-in-search-logs.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Nice write-up from a year ago on K's paper.
]]></description>
<dc:subject>information_retrieval classifiers search_engines kith_and_kin klinkner.kristina jones.rosie</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:e0b39908076b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:classifiers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:search_engines"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:klinkner.kristina"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:jones.rosie"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://bayes.wordpress.com/2009/05/30/alpha-sprouts/">
    <title>Alpha Sprouts « Quantum of Wantum</title>
    <dc:date>2009-05-31T14:18:22+00:00</dc:date>
    <link>http://bayes.wordpress.com/2009/05/30/alpha-sprouts/</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>information_retrieval search_engines good_old_fashioned_ai databases data_analysis wolfram_alpha the_mechanical_turk_of_the_semantic_web arthegall to:blog</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:1f01d105983f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:search_engines"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:good_old_fashioned_ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:databases"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:wolfram_alpha"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:the_mechanical_turk_of_the_semantic_web"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:blog"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cs.berkeley.edu/~brewer/papers/SearchDB.pdf">
    <title>Combining Systems and Databases: A Search Engine Retrospective</title>
    <dc:date>2009-05-31T14:03:10+00:00</dc:date>
    <link>http://www.cs.berkeley.edu/~brewer/papers/SearchDB.pdf</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[I won't actually teach this in 350, but I should probably mention it.
]]></description>
<dc:subject>databases information_retrieval to_teach:data-mining via:arthegall</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:18276d1b6a42/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:databases"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.zylstra.org/blog/archives/2009/05/wolframalpha_ge.html">
    <title>Ton's Interdependent Thoughts: WolframAlpha, Getting Less Impressed Upon Closer Look</title>
    <dc:date>2009-05-05T13:16:56+00:00</dc:date>
    <link>http://www.zylstra.org/blog/archives/2009/05/wolframalpha_ge.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Nice: "For all its coolness on the front of WolframAlpha, on the back end this sounds like it's the mechanical turk of the semantic web."`
]]></description>
<dc:subject>information_retrieval wolfram_alpha via:arthegall wolfram.stephen the_mechanical_turk_of_the_semantic_web</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:9eb808d4f12e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:wolfram_alpha"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:arthegall"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:wolfram.stephen"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:the_mechanical_turk_of_the_semantic_web"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://infolab.stanford.edu/~wangz/project/imsearch/review/JOUR/">
    <title>Content Based Image Retrieval CBIR Survey Paper - 2008</title>
    <dc:date>2009-04-30T23:43:09+00:00</dc:date>
    <link>http://infolab.stanford.edu/~wangz/project/imsearch/review/JOUR/</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>information_retrieval image_retrieval to:NB to_teach:data-mining via:chl</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:180c42a1234b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:image_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:chl"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://icanhascheezburger.com/2007/01/11/this-is-relevant-to-my-interests-2/">
    <title>This is relevant to my interests « I Can Has Cheezburger?</title>
    <dc:date>2009-04-30T13:05:07+00:00</dc:date>
    <link>http://icanhascheezburger.com/2007/01/11/this-is-relevant-to-my-interests-2/</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[To illustrate search assessment and Rocchio's algorithm.
]]></description>
<dc:subject>lolcats funny:geeky to_teach:data-mining information_retrieval</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:9bf4541e6902/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:lolcats"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:funny:geeky"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.semanticuniverse.com/blogs-i-was-positively-impressed-wolfram-alpha.html">
    <title>Doug Lenat - I was positively impressed with Wolfram Alpha</title>
    <dc:date>2009-04-27T22:21:11+00:00</dc:date>
    <link>http://www.semanticuniverse.com/blogs-i-was-positively-impressed-wolfram-alpha.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[... but note carefully why.
]]></description>
<dc:subject>information_retrieval good_old_fashioned_ai databases lenat.douglas wolfram.stephen the_mechanical_turk_of_the_semantic_web</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:33a052946e61/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:good_old_fashioned_ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:databases"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:lenat.douglas"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:wolfram.stephen"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:the_mechanical_turk_of_the_semantic_web"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0807.2569">
    <title>[0807.2569] Text Data Mining: Theory and Methods</title>
    <dc:date>2008-07-25T15:38:55+00:00</dc:date>
    <link>http://arxiv.org/abs/0807.2569</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>to_teach:data-mining data_mining information_retrieval natural_language_processing text_mining</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:d7bbe3502378/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:data_mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:natural_language_processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:text_mining"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0807.3755">
    <title>[0807.3755] Approximating Document Frequency with Term Count Values</title>
    <dc:date>2008-07-25T15:36:57+00:00</dc:date>
    <link>http://arxiv.org/abs/0807.3755</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>information_retrieval to_teach:data-mining</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:6c9dd27afaca/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://xstructure.inr.ac.ru/about.htm">
    <title>About XStructure</title>
    <dc:date>2008-07-21T14:44:34+00:00</dc:date>
    <link>http://xstructure.inr.ac.ru/about.htm</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Interface to arxiv via some kind of hierarchical clustering of the citation graph.  (Can't find details.)  Interesting but doesn't look all that useful (yet).
]]></description>
<dc:subject>community_discovery hierarchical_structure information_retrieval arxiv</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:66238d84e3f3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:community_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hierarchical_structure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:arxiv"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0807.1560">
    <title>[0807.1560] Scientific Paper Summarization Using Citation Summary Networks</title>
    <dc:date>2008-07-15T01:50:49+00:00</dc:date>
    <link>http://arxiv.org/abs/0807.1560</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>information_retrieval cognitive_triage document_summarization to:NB citation_networks meaning_as_location_in_a_system_of_relations to_read radev.dragomir</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:fe94cbc5b137/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cognitive_triage"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:document_summarization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:citation_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:meaning_as_location_in_a_system_of_relations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:radev.dragomir"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.nybooks.com/articles/21514">
    <title>The Library in the New Age - The New York Review of Books</title>
    <dc:date>2008-05-26T16:04:44+00:00</dc:date>
    <link>http://www.nybooks.com/articles/21514</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Some good points, but surprisingly bad history (Chinese printing didn't take off, "The Web began as a means of communication among physicists in 1981"!) from a professional historian.  Not material to the  mostly-sound recommendations.
]]></description>
<dc:subject>books research libraries internet google information_retrieval via:idlethink academia history_of_intellect bibliography journalism newspapers enlightenment computer_networks_as_provinces_of_the_commonwealth_of_letters blogs why_oh_why_cant_we_have_a_better_press_corps why_oh_why_cant_we_have_a_better_academic_publishing_system natural_history_of_truthiness social_life_of_the_mind darnton.robert</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:d044c23a041e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:books"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:libraries"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:internet"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:google"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:idlethink"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:academia"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:history_of_intellect"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bibliography"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:journalism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:newspapers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:enlightenment"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:computer_networks_as_provinces_of_the_commonwealth_of_letters"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:blogs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:why_oh_why_cant_we_have_a_better_press_corps"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:why_oh_why_cant_we_have_a_better_academic_publishing_system"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:natural_history_of_truthiness"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:social_life_of_the_mind"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:darnton.robert"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.uic.edu/htbin/cgiwrap/bin/ojs/index.php/fm/article/view/2008">
    <title>Desperately seeking the consumer: Personalized search engines and the commercial exploitation of user data: Rohle</title>
    <dc:date>2008-03-17T13:38:41+00:00</dc:date>
    <link>http://www.uic.edu/htbin/cgiwrap/bin/ojs/index.php/fm/article/view/2008</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[" Essentially, search engines now fulfill the task of translating information needs into consumption needs."
]]></description>
<dc:subject>information_retrieval</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:2e173a475614/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://nlp.cs.nyu.edu/sekine/papers/coling06.pdf">
    <title>On-Demand Information Extraction</title>
    <dc:date>2008-02-25T16:13:43+00:00</dc:date>
    <link>http://nlp.cs.nyu.edu/sekine/papers/coling06.pdf</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>information_retrieval machine_learning data_mining pattern_discovery via:klk</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:5f2404614ac5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:machine_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:data_mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:pattern_discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:klk"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.ipam.ucla.edu/schedule.aspx?pc=sews1">
    <title>Workshop I: Dynamic Searches and Knowledge Building</title>
    <dc:date>2007-11-27T23:34:00+00:00</dc:date>
    <link>https://www.ipam.ucla.edu/schedule.aspx?pc=sews1</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[IPAM workshop on the mathematics of search and knowledge discovery, with links to slides and/or audio for some talks
]]></description>
<dc:subject>information_retrieval machine_learning data_mining linguistics natural_language_processing via:klk semantics_from_syntax</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:a47ac1d2f58e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:machine_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:data_mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:linguistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:natural_language_processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:via:klk"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:semantics_from_syntax"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0708.3601">
    <title>[0708.3601] A correlated topic model of Science</title>
    <dc:date>2007-11-16T01:46:07+00:00</dc:date>
    <link>http://arxiv.org/abs/0708.3601</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>statistics information_retrieval text_mining in_NB</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:53882834b3a6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:text_mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/0710.3972">
    <title>[0710.3972] Entropy Rank and Free Energy: a thermodynamic formalism for Web search</title>
    <dc:date>2007-11-10T01:30:48+00:00</dc:date>
    <link>http://arxiv.org/abs/0710.3972</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["variants of PageRank ... based on Ruelle's thermodynamic formalism"
]]></description>
<dc:subject>to:NB information_retrieval page_rank thermodynamic_formalism</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:571ec2977a8c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:page_rank"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:thermodynamic_formalism"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.cs.brown.edu/~th/papers/Hofmann-UAI99.pdf">
    <title>Probabilistic Latent Semantic Analysis (Hofmann)</title>
    <dc:date>2007-11-09T19:39:27+00:00</dc:date>
    <link>http://www.cs.brown.edu/~th/papers/Hofmann-UAI99.pdf</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>latent_semantic_analysis graphical_models computational_statistics information_retrieval to_teach:data-mining in_NB hofmann.thomas</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:911f9ef6a333/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:latent_semantic_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:graphical_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:computational_statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hofmann.thomas"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://itre.cis.upenn.edu/~myl/languagelog/archives/005086.html">
    <title>Language Log: Solving the mysteries of the ages via semantic search</title>
    <dc:date>2007-11-04T13:28:02+00:00</dc:date>
    <link>http://itre.cis.upenn.edu/~myl/languagelog/archives/005086.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[Some of these are almost in the "good vodka, rotten meat" league...
]]></description>
<dc:subject>information_retrieval funny:geeky</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:b348401d9b81/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:funny:geeky"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://michaelnielsen.org/blog/?p=283">
    <title>Michael Nielsen » Information Aggregators</title>
    <dc:date>2007-11-02T17:30:30+00:00</dc:date>
    <link>http://michaelnielsen.org/blog/?p=283</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Where are the programming languages that have Bayesian filters, PageRank, and other types of collective intelligence as a central, core part of the language? I don’t mean libraries or plugines, I mean integrated into the core of the language in the sam
]]></description>
<dc:subject>collaborative_filtering information_retrieval social_media the_web cognitive_triage</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:867fdcc13c7e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:collaborative_filtering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:social_media"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:the_web"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cognitive_triage"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://research.google.com/pubs/papers.html">
    <title>Papers Written by Googlers</title>
    <dc:date>2007-10-18T16:34:31+00:00</dc:date>
    <link>http://research.google.com/pubs/papers.html</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>data_mining networks theoretical_computer_science algorithms distributed_systems scientific_computing bioinformatics natural_language_processing information_retrieval</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:3a3ae33c3a62/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:data_mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:theoretical_computer_science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:distributed_systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:scientific_computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:natural_language_processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.google.com/technology/pigeonrank.html">
    <title>PigeonRank</title>
    <dc:date>2007-10-13T14:21:13+00:00</dc:date>
    <link>http://www.google.com/technology/pigeonrank.html</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[building upon the breakthrough research of B. F. Skinner
]]></description>
<dc:subject>google search_engines behaviorism reinforcement_learning funny:geeky information_retrieval to_teach:data-mining skinner.b.f.</dc:subject>
<dc:identifier>https://pinboard.in/u:cshalizi/b:d7522718bc8b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:google"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:search_engines"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:behaviorism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:reinforcement_learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:funny:geeky"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_retrieval"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:skinner.b.f."/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>