关键词: 历史兴趣网页, 历史查询词, 个性化查询扩展, 词间相关度, 搜索引擎

Abstract: The current mainstream web search engines have many shortcomings such as the deficiency of personalization and the low precision. By introducing several improved techniques into a current algorithm, a new personalized query expansion method based on user’s historical interested web pages and historical query terms 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 according to the current user’s interest profile. More personalized expansion words then will be generated by the proposed algorithm and be submitted to the search engine together with the query keyword. Thereby 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.

Key words: historical interested web pages, historical query terms, personalized query expansion, term-term associations, search engine