摘要
运用查询扩展中的局部反馈技术和伪文档反馈技术,提出一种面向微博的查询扩展方法。将候选词分为3个层级进行考察,分别为主题-词语层、文档-词语层和词语-词语层,对应3个层次提出权重计算方法和相似度计算方法。最后,通过实验对方法进行分析比较,实验结果显示,综合考虑主题-词语权重和文档-词语权重得到的扩展词更能满足用户的需求。
In this paper, a query expansion method was proposed for micro-blog, which uses local query expansion and pseudo-feedback technology documentation feedback technology. We divides candidate words into three levels, respectively theme-words layer, documents-word layer and the words-words layer, corresponding to the three levels proposed similarity calculation method of calculation and weights. Finally, experiments were analyzed by the method. The experimental results show that, the received extended-words considering the topic-word weights and documents-word weights were better to meet the users' satisfaction.
出处
《图书情报工作》
CSSCI
北大核心
2014年第1期130-135,共6页
Library and Information Service
基金
国家自然科学基金项目"社会化媒体集成检索与语义分析方法研究"(项目编号:71273194)
武汉大学2013年研究生自主科研项目(项目编号:2013104010206)研究成果之一