Query expansion using web access log files

  • Authors:
  • Yun Zhu;Le Gruenwald

  • Affiliations:
  • The University of Oklahoma, Norman, OK;The University of Oklahoma, Norman, OK

  • Venue:
  • DEXA'05 Proceedings of the 16th international conference on Database and Expert Systems Applications
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Query Expansion has long been recognized as one of the effective methods in solving short queries and improving ranking accuracy in traditional IR research. Many variations of this method have been introduced throughout the past decades; however, few of them have incorporated web log information into the query expansion process. In this paper, we propose an expansion technique that expands document content at the initial index stage using queries extracted from the web log files. Our experimental results show that even with a minimal amount of real world log information available and a professionally cataloged knowledge structure to aid the search, there is still a significant improvement in using our query expansion method compared to the conventional query expansion ones.