Abstract
Current popular search engines are built to serve all users, independent of the needs of any individual user. A personalized query expansion method based on user's historical interested Web pages (UHIWPs) and user’s historical query terms (UHQTs) is proposed in this paper. When a user submits a query keyword to a search engine, the new algorithm can automatically locate the current user’s implicit search intention and compute the term-term associations dynamically according to the user’s UHIWPs and UHQTs. More personalized expansion terms then will be generated and submitted to the search engine together with the query keyword. As a result, different search results can be returned to different users even though they input the same query keywords. Experimental results show that this method is better than the current algorithm in average precision.
Publisher
Trans Tech Publications, Ltd.
Reference13 articles.
1. Micro Speretta, Susan Gauch: Personalized Research Based on User Search Histories [C]. Proceedings of the 2005 IEEE/WIC/ACM International Conference on Web Intelligence (WI'05).
2. T. Haveliwala: Topic-Sensitive PageRank [C]. In Proceedings of the Eleventh Intel World Wide Web Conf., (2002).
3. Carolyn J. Crouch, Donald B. Crouch et al: Improving the retrieval effectiveness of very short queries [J]. Information Processing and Management (S0306-4573), 2002, 38(1): 1-36.
4. M Shamim Khan, Sebastian Khor. Enhanced web document retrieval using automatic query expansion [J]. Journal of the American Society for Information Science and Technology (S1532-2882), 2004, 55(1): 29-40.
5. Ding Guodong, Bai Shuo et al: Local Co-occurrence Based Query Expansion for Information Retrieval [J]. Journal of Chinese Information Processing (Chinese), Vol. 20, No. 3, 2006, pp.48-53.