Abstract

This work presents a method for online generation of query related suggestions for a Web search engine. The method uses association rules to extract related queries from the log of sbumitted queries to the search engine. Experimental results were performed on a real log containing more than 2.3 million queries submitted to a commercial search engine. For the top 5 related terms our method presented correct suggestions in 90.5\% of the time. Using queries randomly selected from a log we obtained 93.45\% of correct suggestions. A study of the user behavior showed that in 92.23\% of the clicks on suggestions, users found useful information. The same approach can be used to provide terms to the classic problem of query expansion. For instance, the average precision of the answers of the Google search engine was improved by 23.16\% using our aproach as a query expansion method.

Links and resources

Tags

community

  • @brusilovsky
  • @aho
@brusilovsky's tags highlighted