Social Network Analysis of yahoo web-search engine query logs

TL;DR

This paper constructs query networks from Yahoo web search logs, representing queries as nodes and their semantic relatedness as edges, to better understand user search interests.

Contribution

It introduces a method to build and analyze query networks from search logs, highlighting semantic relationships between user queries.

Findings

Query networks reveal patterns in user search behavior

Semantic relatedness between queries can be effectively modeled

Insights can improve search engine relevance

Abstract

Web is now the undisputed warehouse for information. It can now provide most of the answers for modern problems. Search engines do a great job by combining and ranking the best results when the users try to search for any particular information. However, as we know 'with great power comes great responsibility', it is not an easy task for data analysts to find the most relevant information for the queries. One major challenge is that web search engines face difficulties in recognizing users' specific search interests given his initial query. In this project, we have tried to build query networks from web search engine query logs, with the nodes representing queries and the edges exhibiting the semantic relatedness between Queries.