@article{silverstein1999analysis,
  abstract = {In this paper we present an analysis of an AltaVista Search Engine query log consisting of approximately 1 billion entries for search requests over a period of six weeks. This represents almost 285 million user sessions, each an attempt to fill a single information need. We present an analysis of individual queries, query duplication, and query sessions. We also present results of a correlation analysis of the log entries, studying the interaction of terms within queries. Our data supports the conjecture that web users differ significantly from the user assumed in the standard information retrieval literature. Specifically, we show that web users type in short queries, mostly look at the first 10 results only, and seldom modify the query. This suggests that traditional information retrieval techniques may not work well for answering web search requests. The correlation analysis showed that the most highly correlated items are constituents of phrases. This result indicates it may be useful for search engines to consider search terms as parts of phrases even if the user did not explicitly specify them as such.},
  acmid = {331405},
  address = {New York, NY, USA},
  author = {Silverstein, Craig and Marais, Hannes and Henzinger, Monika and Moricz, Michael},
  doi = {10.1145/331403.331405},
  interhash = {5e26846be504d4fc6b6a7b236c1c023a},
  intrahash = {4ac734beeccbcb3a05786e8ca57f5629},
  issn = {0163-5840},
  issue_date = {Fall 1999},
  journal = {SIGIR Forum},
  month = sep,
  number = 1,
  numpages = {7},
  pages = {6--12},
  publisher = {ACM},
  title = {Analysis of a very large web search engine query log},
  url = {http://doi.acm.org/10.1145/331403.331405},
  volume = 33,
  year = 1999
}

@inproceedings{1526880,
  abstract = {Given only the URL of a web page, can we identify its topic? This is the question that we examine in this paper. Usually, web pages are classified using their content, but a URL-only classifier is preferable, (i) when speed is crucial, (ii) to enable content filtering before an (objection-able) web page is downloaded, (iii) when a page's content is hidden in images, (iv) to annotate hyperlinks in a personalized web browser, without fetching the target page, and (v) when a focused crawler wants to infer the topic of a target page before devoting bandwidth to download it. We apply a machine learning approach to the topic identification task and evaluate its performance in extensive experiments on categorized web pages from the Open Directory Project (ODP). When training separate binary classifiers for each topic, we achieve typical F-measure values between 80 and 85, and a typical precision of around 85. We also ran experiments on a small data set of university web pages. For the task of classifying these pages into faculty, student, course and project pages, our methods improve over previous approaches by 13.8 points of F-measure.},
  address = {New York, NY, USA},
  author = {Baykan, Eda and Henzinger, Monika and Marian, Ludmila and Weber, Ingmar},
  booktitle = {WWW '09: Proceedings of the 18th international conference on World wide web},
  doi = {http://doi.acm.org/10.1145/1526709.1526880},
  interhash = {2c31fb50c5a407a5ecbaf832090acd97},
  intrahash = {a9f20eb7a52df3b1a32efc010d0361a1},
  isbn = {978-1-60558-487-4},
  location = {Madrid, Spain},
  pages = {1109--1110},
  publisher = {ACM},
  title = {Purely URL-based topic classification},
  url = {http://portal.acm.org/citation.cfm?id=1526880},
  year = 2009
}