一种融合聚类和时间信息的微博排序新方法  

Combining Cluster and Temporal Information for Microblog Search

作　　者：卫冰洁[1,2] 史亮[2] 王斌[3] 

机构地区：[1]中国科学院计算技术研究所,北京100190 [2]国家计算机网络应急技术处理协调中心,北京100029 [3]中国科学院信息工程研究所,北京100093

出　　处：《中文信息学报》2015年第3期177-183,189,共8页Journal of Chinese Information Processing

基　　金：科技支撑计划(2012BAH46B02)

摘　　要：随着微博的快速发展,微博检索已经成为近年来研究领域的热点之一。微博检索与传统文本检索在两个方面明显不同:一是微博具有自己的特点,表现在文本短和内容中具有主题概括词(称为Hashtag);二是微博排序中除了考虑文本和语义相似度,还需考虑时间信息。根据这两点区别,该文在统计语言模型的基础上,使用聚类进行文本扩展,并将Hashtag信息运用到聚类过程中。同时,因为微博数据集中具有Hashtag的微博个数不超过13%,针对这一现象,该文还提出了一种扩展微博Hashtag的方法,最终提出了基于聚类的三个模型。然后通过定义文档先验将时间信息加入到提出的三个检索模型中,得到融入聚类和时间信息的三个模型。最后基于TREC Microblog数据的实验结果证明,融合聚类信息和时间信息的模型在MAP和P@30上有明显提高,分别提高7.1%和11.6%。With the rapid development of microblog, microblog retrieval has become a hot research topic in recent years. In contrast to traditional text retrieval, microblog search significantly differs in two aspects. One is that mi- croblog has its own text features, i.e. short text and Hashtag as the theme term. The other is that microblog search should consider the time information and text and semantic similarity. This paper addresses the above issue by clus- tering to expand text content. The hashtag is introduced into the clustering, and, to guarantee its effect, a method to enrich the Hashtag in a microblog is described. Finally we used the time information as the document＇s prior and altogether three models are examined in the experments. Experiments on TREC Microblog dataset show that our models significantly improved MAP and P@30 with 7.1% and 11.6 % increase separately.

关 键 词：微博检索 Hashtag 聚类 时间 语言模型 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]