期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2014
卷号：5
期号：1
页码：20-24
出版社：TechScience Publications
摘要：Nowadays Internet is widely used by users to satisfy various information needs. However, ambiguous query/topic submitted to search engine doesn’t satisfy user information needs, because different users may have different information needs on diverse aspects upon submission of same query/topic to search engine. So discovering different user search goals becomes complicated. The evaluation and depiction of user search goals can be very useful in improving search engine relevance and user knowledge. This paper proposes a novel approach for inferring user search goals by analyzing user query logs from various search engines. The proposed approach is used to discover different user search goals for a query by clustering the user feedback sessions. Feedback sessions are constructed from clickthrough logs of various search engines. The method first generates pseudo-documents to better represent feedback sessions for clustering. Finally, clustering pseudo-documents to discover different user search goals and depict them with some keywords. Then these user search goals are used to restructure the web search results.
