计算机应用 ›› 2014, Vol. 34 ›› Issue (2): 486-490.

• 人工智能 • 上一篇    下一篇

基于突发词聚类的微博突发事件检测方法

郭跇秀,吕学强,李卓   

  1. 网络文化与数字传播北京市重点实验室(北京信息科技大学),北京 100101
  • 收稿日期:2013-08-06 修回日期:2013-10-14 出版日期:2014-02-01 发布日期:2014-03-01
  • 通讯作者: 郭跇秀
  • 作者简介:郭跇秀(1985-),男,黑龙江哈尔滨人,硕士研究生,CCF会员,主要研究方向:自然语言处理、数据挖掘;吕学强(1970-),男,山东鱼台人,教授,博士,CCF会员,主要研究方向:自然语言与多媒体信息处理;李卓(1983-),男,河南南阳人,讲师,博士,CCF会员,主要研究方向:无线网路、移动计算。
  • 基金资助:
    国家自然科学基金资助项目;北京市教委科技发展计划重点项目暨北京市自然科学基金B类重点项目

Bursty topics detection approach on Chinese microblog based on burst words clustering

GUO Yixiu,LYU Xueqiang,LI Zhuo   

  1. Beijing Key Laboratory of Internet Culture and Digital Dissemination Research(Beijing Information Science and Technology University), Beijing 100101,China
  • Received:2013-08-06 Revised:2013-10-14 Online:2014-02-01 Published:2014-03-01
  • Contact: GUO Yixiu

摘要: 微博突发事件检测是网络舆情分析的重要分支,近年来已受到国内外学者的广泛关注。分析用户行为特征,提出一种用户影响力计算方法,并将其与微博文本特征、传播特征相结合,提出词语突发度概念作为突发词的判定标准,进而抽取突发词集;引入凝聚式层次聚类算法,对突发词集进行聚类,并筛选出合适的突发词类簇用以描述突发事件,从而实现微博突发事件检测。通过实验检测,结果是正确率为63.64%,召回率为87.5%,F值为0.74,表明该方法可以在大量微博数据中有效检测到突发事件。

关键词: 突发事件, 用户影响力, 突发词, 聚类

Abstract: Bursty topics detection on microblog is an import branch of online public opinion analysis, and has attracted much attention from international scholars. In this paper, a new approach of calculating users' influence was proposed based on the analysis of users' behavior characteristics. Combining the user influence with text features and propagation features, this paper defined a concept named Bursty which is used to judge if a word was a burst word. Being judged by Bursty, burst words can be extracted from microblog corpus. Hierarchical clustering algorithm was introduced to cluster the burst words and chose appropriate burst word clusters to describe bursty topics on microblog in order to realize bursty topics detection on microblog. In experiments, the precision, recall and F-measure reached 63.64%,87.5% and 74% respectively. The method is proved effective on bursty topic detection based on mass microblog data.

Key words: bursty topic, users' influence, burst word, clustering

中图分类号: