CLHQS: Hierarchical Query Suggestion by Mining Clickthrough Log

Authors:
Depin Chen;Ning Liu;Zhijun Yin;Yang Tong;Jun Yan;Zheng Chen
Affiliations:
University of Science and Technology of China,;Microsoft Research Asia,;University of Illinois at Urbana-Champaign,;Microsoft Research Asia,;Microsoft Research Asia,;Microsoft Research Asia,
Venue:
PAKDD '09 Proceedings of the 13th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining
Year:
2009

Citing 6
Cited 0

Learning String-Edit Distance

IEEE Transactions on Pattern Analysis and Machine Intelligence
An Evaluation of Statistical Approaches to Text Categorization

Information Retrieval
Relevant term suggestion in interactive web search based on contextual information in query session logs

Journal of the American Society for Information Science and Technology
Mining search engine query logs for query recommendation

Proceedings of the 15th international conference on World Wide Web
Query suggestion based on user landing pages

SIGIR '07 Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval
Context-aware query suggestion by mining click-through and session data

Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining

Quantified Score

Hi-index	0.00

Visualization

Abstract

Most commercial search engines provide query suggestion in a ranked list for more effective search. However, a ranked list may not be an ideal way to satisfy users' various information demands. In this paper, we propose a novel query suggestion method named CLHQS (Clickthrough-Log based Hierarchical Query Suggestion). It organizes the suggested queries into a well-structured hierarchy. Users can easily generalize, extend or specialize their queries within the hierarchy. The query hierarchy is mined from the clickthrough log data in the following way. First, we generate a candidate set through the query-url graph analysis. Second, the pair-wise relationships are inspected for each pair of candidate queries. Finally, we construct the suggested query hierarchy using these relationships. Experiments on a real-world clickthrough log validate the effectiveness of our proposed CLHQS approach.