突发事件新闻报道与微博信息的爆发性模式比较被引量：19

Comparison of Burst Pattern Between News Reports and Microblog Information on Emergency Events

下载PDF

导出

摘要 Web信息流是突发事件监控预警中重要的信息来源，通过研究信息流的爆发特性可以及时的了解事件发展的状态。利用隐马尔可夫模型对新闻渠道和微博两种渠道的信息爆发性模式进行了分析，对28起突发事件进行了实验研究。对两种渠道的信息爆发模式上进行了比较，实验结果表明两种渠道在信息爆发模式上存在差异，这种差异不仅与突发事件类型有关，而且与突发事件的等级有关。进而对两种渠道信息传播的时效性进行了研究，结果表明微博信息演化过程快于新闻报道。结论对于突发事件监控预警具有实际的指导意义。 Web information is the important information source for su^eillance in emergency events, people can learn the status of the emergency through studying the burst of information stream. This paper proposed a method to model the burst of the information and compared the burst models between news reports and microblog information on emergency events through analyzing the 28 emergency events. The experimental results show that the burst models between the two channels are different, and the difference not only depends on the type of event, but also depends on the level of the emergency. Furtherly this paper analyzed the speed of the information burst between the news report and the microblog,the experimental result shows the microblog information is faster than news report in the burst speed. The conclusions are meaningful for the surveillance in emergency.

作者刘志明刘鲁苗蕊

机构地区华南农业大学公共管理学院北京航空航天大学经济管理学院东北财经大学管理科学与工程学院

出处《情报学报》 CSSCI 北大核心 2013年第3期288-298,共11页 Journal of the China Society for Scientific and Technical Information

基金国家自然科学基金资助项目(No.90924020) 高等学校博士学科点专项科研基金(No.200800060005)

关键词突发事件爆发模式隐马尔可夫模型新闻报道微博 emergency event, burst mode, hidden Markov model, news reports, nicroblog

分类号 G206 [文化科学—传播学]

引文网络
相关文献

参考文献26

1中华人民共和国中央人民政府.中华人民共和国突发事件应对法[N].http://www.gov.cn/flfg/2007-08/30/content_732593.htm[2012-03-13].
2Sarah Vieweg, Amanda L. Hughes, Kate Starbird, et al. Microblogging During Two Natural Hazards Events: What Twitter May Contribute to Situational Awareness [ C ]. Atlanta, GA, USA ,2010 : 10-15.
3Takeshi Sakaki ,Makoto Okazaki ,Yutaka Matsuo. Earthquake Shakes Twitter Users: Real-time Event Detection by Social Sensors [C]. WWW2010, Raleigh, North Carolina, 2010:26-30.
4Marc Cheong, Vincent C. S. Lee. A microblogging-based approach to terrorism informatics : Exploration and chronicling civilian sentiment and response to terrorism events via Twitter [ J]. Information Systems Frontiers, 2010 : 1-15.
5Aron Culotta. Towards detecting influenza epidemics by analyzing Twitter messages [ C ]. 1st Workshop on Social Media Analytics, Washington, DC, USA ,July 25,2010.
6Thomas Heverin, Lisl Zach. Microblogging for Crisis Communication : Examination of Twitter Use in Response to a 2009 Violent Crisis in the Seattle-Tacoma, Washington Area [ C]//Proceedings of the 7^th International ISCRAM Conference-Seattle, USA, May 2010.
7Swan R, Allan J. Extracting significant time varying features from text [ C ]//Proceedings of the eighth international conference on Information and knowledge management, 1999.
8Swan R, Allan J. Automatic generation of overview timeliness [ C ]//In Proc. SIGIR Intl. Conf. Information Retrieval, 2000.
9Zhu Y, Shasha D. Efficient Elastic Burst Detection in Data Streams [ C ]//Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining. Washington, D. C, 2003 : 24-27.
10Kleinberg J. Bursty and hierarchical structure in streams [ J ]. Data Mining and Knowledge Discovery, 2003, 7(4) : 373-397.

二级参考文献20

1戴媛,姚飞.基于网络舆情安全的信息挖掘及评估指标体系研究[J].情报理论与实践,2008,31(6):873-876. 被引量：75
2徐寅峰,马丽娟,刘德海.信息交流在公共卫生突发事件处理中作用的博弈分析[J].系统工程,2005,23(1):21-27. 被引量：19
3谢海光,陈中润.互联网内容及舆情深度分析模式[J].中国青年政治学院学报,2006,25(3):95-100. 被引量：113
4(美)Pang-NingTan,(美)MichaelSteinbach,(美)VipinKumar著,范明,范宏建等.数据挖掘导论[M]人民邮电出版社,2006.
5Jon Kleinberg.Bursty and Hierarchical Structure in Streams[J]. Data Mining and Knowledge Discovery . 2003 (4)
6Center for Disease Control(CDC).Crisis andemergency risk communication. http://www.au.af.mil/au/awc/awcgate/cdc/cerc book.pdf .
7Swan R,Allan J.Extracting significant timevarying features from text. Proceedings ofthe 8th ACM Conference on Information andKnowledge Management . 1999
8Zhu Y,Shasha D.Efficient elastic burst detectionin data streams. Proceedings of the 9th ACMSIGKDD International Conference on KnowledgeDiscovery and Data Mining . 2003
9Yi J.Detecting buzz from time-sequenced documentstreams. Proceedings of the 2005 IEEE Inter-national Conference on e-Technology,e-Commerceand e-Service . 2005
10Chen,et al.An adaptive threshold framework forevent detection using HMM-based life profiles. ACM Transactions on Information Systems . 2009