Exploring features for the automatic identification of user goals in web search

  • Herrera M
  • de Moura E
  • Cristo M
 et al. 
  • 42

    Readers

    Mendeley users who have this article in their library.
  • 16

    Citations

    Citations of this article.

Abstract

Queries submitted to search engines can be classified according to the user goals into three distinct categories: navigational, informational, and transactional. Such classification may be useful, for instance, as additional information for advertisement selection algorithms and for search engine ranking functions, among other possible applications. This paper presents a study about the impact of using several features extracted from the document collection and query logs on the task of automatically identifying the users' goals behind their queries. We propose the use of new features not previously reported in literature and study their impact on the quality of the query classification task. Further, we study the impact of each feature on different web collections, showing that the choice of the best set of features may change according to the target collection. The results obtained indicate the new proposed set of features improves the quality of the classification task when compared to previous proposals. We report experiments with two web collections where we were able to obtain 82.5% and 77.67% of overall accuracy when classifying queries according to the three distinct user goals studied. © 2009 Elsevier Ltd. All rights reserved.

Author-supplied keywords

  • Information retrieval
  • Machine learning
  • Query classification
  • SVM
  • Web search

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Authors

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free