Events Detection and Temporal Analysis In Social Media

摘要：

　　In the past few years,event detection has drawn a lot of attention.We proposed an ecient method to detect event in this paper.An event is dened as a set of descriptive,collocated keywords in this paper.Intuitively,documents that describe the same event will contain similar sets of keywords.Individual events will form clusters in the graph of keywords for a document collection.We built a network of keywords based on their co-occurrence in documents.We proposed an ecient method which create a keywords weight directed graph named KeyGraph and use community detection method to discover events.Clump of key-words describing an event can be used to analyse the trend of the event.The accuracy of detecting events is over eighty percents with our method.

关键词： Event Detection KeyGraph Co-occurrence Temporal Analysis

作者: Yawei Jia Jing Xu Zhonghu Xu Kai Xing

作者单位: University of Science and Technology of China No. 443,Huangshan Road,Shushan District,Hefei,Anhui 230027

会议类型: 国际会议

会议名称: 第五届自然语言处理与中文计算会议(NLPCC-ICCPOL2016)

会议地点: 昆明

会议语种:英文

页码: 1-12

在线出版日期: 2016-12-02（万方平台首次上网日期，不代表论文的发表时间）