Analysis of a very large web search engine query log Export

@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.}, address = {New York, NY, USA}, author = {Silverstein, Craig and Marais, Hannes and Henzinger, Monika and Moricz, Michael}, citeulike-article-id = {1126}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=331405}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/331403.331405}, doi = {10.1145/331403.331405}, issn = {0163-5840}, journal = {SIGIR Forum}, keywords = {information\_retrieval, query\_log, query\_sessions, web\_search\_engine}, number = {1}, pages = {6--12}, posted-at = {2009-10-28 07:40:03}, priority = {2}, publisher = {ACM}, title = {Analysis of a very large web search engine query log}, url = {http://dx.doi.org/10.1145/331403.331405}, volume = {33}, year = {1999} }

TY - JOUR ID - silverstein1999analysis L3 - citeulike-article-id:1126 N2 - 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. IS - 1 JF - SIGIR Forum SN - 0163-5840 AD - New York, NY, USA EP - 12 TI - Analysis of a very large web search engine query log PB - ACM VL - 33 SP - 6 KW - information_retrieval KW - query_log KW - query_sessions KW - web_search_engine AU - Silverstein, Craig AU - Marais, Hannes AU - Henzinger, Monika AU - Moricz, Michael PY - 1999/// UR - http://dx.doi.org/10.1145/331403.331405 ER -