关于用户行为分析搜索引擎自动性能评价.PDFVIP

xxxx-xxxx/xxxx/xx(xx)xxxx ©2007 Journal of Software 软 件 学 报 Vol.xx, No.x ∗ 基于用户行为分析的搜索引擎自动性能评价 1+ 2 3 4 5 刘奕群 , 岑荣伟 , 张敏 , 茹立云 , 马少平 ， ， ， 1 2 3 5(清华大学 智能技术与系统国家重点实验室,北京 100084) 4 (搜狐公司研发中心,北京 100084) * Automatic Search Engine Evaluation Based On User Behavior Analysis 1+ 2 3 4 5 LIU Yi-qun , CEN Rongwei , ZHANG Min , RU Liyun , MA Shao-ping 1, 2, 3,5(State Key Lab of Intelligent Technology and Systems, Tsinghua University, Beijing 100084, China) 4 (Sohu Inc. Research and Development Center, Beijing 100084, China) + Corresponding author: Phn: +86-10 Fax: +86-10 E-mail: liuyiqun03@. , Abstract : Performance evaluation is an important issue in Web search engine researches. Traditional evaluation methods rely on much human efforts and are therefore quite time-consuming. With click-through data analysis, we proposed an automatic search engine performance evaluation method. This method generates navigational type query topics and answers automatically based on search users’ querying and clicking behavior. Experimental results based on a commercial Chinese search engine’s user logs show that the automatically method gets a similar evaluation result with traditional assessor-based ones. Key words: Web Information Retrieval; Performance Evaluation; User Behavior Analysis. 摘 要: 性能评价一直是网络信息检索研究中的核心课题之一。传统的评价方式需要花费大量的人力物力，时 间效率也较低。基于用户行为分析的思路，提出了一种自动进行搜索引擎性能评价的方法，此方法能够自动生成 导航类查询测试集合并对查询对应的标准答案实现自动标注。实验结果证明，此方法能与人工标注的评价取得基 本一致的评价效果，同时大大减少了评价所需的人力、物力资源，并加快了评价反馈周期。 关键词: 网络信息检索;性能评价;用户行为分析 中图法分类号: TP391 TP393