【作者】 时达明； 林鸿飞；

【Author】 Shi Daming Lin Hongfei Department of Computer Science and Engineering,Delian University of Technology,Dalian 116024

【机构】 大连理工大学计算机科学与工程系；

【摘要】 目前对话题识别和话题跟踪的研究非常多,但这大都是对新闻事件进行分析,Blog 是目前 Internet 上一种非常重要的媒体,它可以提供给用户方便地发表自己的观点并可以对其他人的观点进行评论,其中的评论信息是其它新闻事件所不具有的。传统的 Blog 热点话题主要是根据评论数来得到的,并没有考虑评论和话题的内容。为此,本文提出了一种基于内容相关度和语义分析的 Blog 热点话题发现方法。该方法在考虑了评论数量的同时, 还通过分析评论与话题的内容相关度并分析评论中的语义来计算话题在该 Blog 中的热点度,并最终进行该 Blog 热点话题的发现。实验表明,本文的方法是有效的。更多还原

【Abstract】 At present,there are many researches about topic detection and tracking,but these analysis aims at news events, while blog is a very important media on Internet recently,they can provide users with an easy way to express their own opinions and comment on other’s opinions,and news events do not have any comments.Traditional blog hot topic can be obtained according to the number of comments mainly,contents of comments and topics do not be considered.So,this paper presents an approach of blog hot topic discovery based on content relation and semantic analysis.This approach considers the number of comments and computes the Hot Degree of topics by analyzing the contents relation between comments and topics and semantic information simultaneously,at last discoveries hot topic of this biog.Experiments show that the approach in this paper is effective.更多还原