Query intent detection based on query log mining

Juan Zamora, Marcelo Mendoza, Héctor Allende

Research output: Contribution to journalArticlepeer-review

5 Scopus citations

Abstract

In this paper we deal with the problem of automatic detection of query intent in search engines. We studied features that have shown good performance in the state-of-the- art, combined with novel features extracted from click-through data. We show that the combination of these features gives good precision results. In a second stage, four text- based classifiers were studied to test the usefulness of text-based features. With a low rate of false positives (less than 10 %) the proposed classifiers can detect query intent in over 90% of the evaluation instances. However due to a notorious unbalance in the classes, the proposed classifiers show poor results to detect transactional intents. We address this problem by including a cost sensitive learning strategy, allowing to solve the skewed data distribution. Finally, we explore the use of classifier ensembles which allow to us to achieve the best performance for the task.

Original languageEnglish
Pages (from-to)24-52
Number of pages29
JournalJournal of Web Engineering
Volume13
Issue number1-2
StatePublished - 1 Mar 2014
Externally publishedYes

Keywords

  • Query categorization
  • Query logs
  • User intents

Fingerprint

Dive into the research topics of 'Query intent detection based on query log mining'. Together they form a unique fingerprint.

Cite this