期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2014
卷号：3
期号：4
页码：1378-1381
出版社：Shri Pannalal Research Institute of Technolgy
摘要：Users can submit ambiguous queries to the search engine. The search engine provides the relevant information, but it does not match with the user query. To overcome this problem, User search goals can be used. It defines the information needed for a query. To discovers different user search goals for a query by clustering the feedback Sessions. It consists of both clicked and unclicked URLs. Each URL consists of title and snippets. In the proposed system, genetic algorithm can be used to find the optimal solution for the weightage of title and snippet. Second feedback session is mapped to the pseudo document. Clustering the pseudo documents and each cluster can be considered as one search goal and depict them with some keywords or goal text. Evaluation of clustering is an important problem. So, Classified Average Precision can be used to evaluate the performance of user search goals inference and restructuring results.
