期刊名称：International Journal of Computer Science & Technology
印刷版ISSN：2229-4333
电子版ISSN：0976-8491
出版年度：2015
卷号：6
期号：3
页码：196-199
语种：English
出版社：Ayushmaan Technologies
摘要：A search engine is a program that is used to search information on the internet. When an enquiry is issued in search interface, distinct users may have distinct search objectives in mind for the same enquiry. The study of user search objectives is helpful in refining search engine significance and user practice. In the first phase, a model is suggested to find out distinct user search objectives for an enquiry by grouping Feedback sessions. Feedback sessions are shaped from user click logs which can provide information tothe user. In the second phase, a novel approach is recommended to manufacture Pseudo-documents to better denote the Feedback sessions for grouping. In the third phase, a new principle “Classified Average Precision” is proposed to estimate the deduction of user search objectives. By using these user search objectives, results are reorganized. In the last phase, PageRank is applied to obtain ranked results in which most visited URLs are displayed on the top. Results from search engine show the efficiency ofthe proposed method. By using above methodology, users can retrieve their information more efficiently. To improve grouping performance and user search relevance, Fuzzy and bisecting clustering algorithms can be enhanced in future.
关键词：User Search Objectives;Feedback Sessions;Pseudo-Documents; Reorganizing Results;and Classified Average Precision.
