@article{park2005searching,
  abstract = {Transaction logs of NAVER, a major Korean Web search engine, were analyzed to track the information-seeking behavior of Korean Web users. These transaction logs include more than 40 million queries collected over 1 week. This study examines current transaction log analysis methodologies and proposes a method for log cleaning, session definition, and query classification. A term definition method which is necessary for Korean transaction log analysis is also discussed. The results of this study show that users behave in a simple way: they type in short queries with a few query terms, seldom use advanced features, and view few results' pages. Users also behave in a passive way: they seldom change search environments set by the system. It is of interest that users tend to change their queries totally rather than adding or deleting terms to modify the previous queries. The results of this study might contribute to the development of more efficient and effective Web search engines and services.},
  author = {Park, Soyeon and Lee, Joon Ho and Bae, Hee Jin},
  doi = {10.1016/j.lisr.2005.01.013},
  interhash = {143140b40c2a30f960938f40e8a3b141},
  intrahash = {fef68b6d2a607ef462592dd73295328d},
  issn = {0740-8188},
  journal = {Library & Information Science Research},
  number = 2,
  pages = {203 - 221},
  title = {End user searching: A Web log analysis of NAVER, a Korean Web search engine},
  url = {http://www.sciencedirect.com/science/article/pii/S0740818805000083},
  volume = 27,
  year = 2005
}

@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
}