Topic-specific analysis of search queries
J Bar-Ilan, Z Zhu, M Levene - Proceedings of the 2009 workshop on Web …, 2009 - dl.acm.org
J Bar-Ilan, Z Zhu, M Levene
Proceedings of the 2009 workshop on Web Search Click Data, 2009•dl.acm.orgThe analysis of search engine logs is important in order to understand how users interact
with a search engine. Conventional analysis of search engine log data looks at various
metrics such as query and session length aggregated over the full data set. Here we
segment the data according to a top-level ontology of web search and compute the metrics
on a topic by topic basis. Our results show that although for a given metric, such as query
length, the statistics of most classes are similar to the aggregate statistic; there are usually …
with a search engine. Conventional analysis of search engine log data looks at various
metrics such as query and session length aggregated over the full data set. Here we
segment the data according to a top-level ontology of web search and compute the metrics
on a topic by topic basis. Our results show that although for a given metric, such as query
length, the statistics of most classes are similar to the aggregate statistic; there are usually …
The analysis of search engine logs is important in order to understand how users interact with a search engine. Conventional analysis of search engine log data looks at various metrics such as query and session length aggregated over the full data set. Here we segment the data according to a top-level ontology of web search and compute the metrics on a topic by topic basis. Our results show that although for a given metric, such as query length, the statistics of most classes are similar to the aggregate statistic; there are usually some outlier classes which exhibit deviant behavior.
ACM Digital Library