Research on a Topic Evolution Analysis System of Emergency Based on Social Media

doi:10.3969/j.issn.1671-1122.2017.09.023

Abstract

Abstract:

With the development of social media, emergencies spread rapidly in the network, which then affects the situation and takes serious impacts on the public order and social situation. So the research on the evolution of emergency has become an important part of the content security field. By studying the basic properties of emergency, it is found that the evolution process of emergency can be reflected by potential topics with sequential evolutionary structure. Combining with the characteristics of social media content and using the dynamic topic model, this paper designs a topic evolution analysis system of emergency, which analyzes public view tendency and restores the event development process from the two aspects of topic content and topic heat. This system achieves the expected results in the topic analysis of "South Korea deploys the THAAD anti-missile system", and has practical value in the field of situation awareness.

Key words: emergency, topic evolution, dynamic topic model, visualization

CLC Number:

TP393

Zihan WANG, Yuhui WANG, Lei WANG, Xin WANG. Research on a Topic Evolution Analysis System of Emergency Based on Social Media[J]. Netinfo Security, 2017, 17(9): 98-102.

Figures/Tables 5

References 15

[1]	赵旭剑, 杨春明, 李波,等. 一种基于特征演变的新闻话题演化挖掘方法[J]. 计算机学报, 2014(4):819-832.
[2]	李凌云, 敖吉, 乔治,等. 基于微博的安全事件实时监测框架研究[J]. 信息网络安全, 2015(1):16-23.
[3]	曹丽娜, 唐锡晋. 基于主题模型的BBS话题演化趋势分析[J]. 管理科学学报, 2014, 17(11):109-121.
[4]	MEI Qiaozhu, ZHAI Chengxiang.Discovering Evolutionary Theme Patterns from Text: An Exploration of Temporal text Mining[C]//KDD. 2005 KDD/Proceedings of the Eleventh ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 21-24, 2005. Chicago, Illinois, USA. New York:ACM, 2005:198-207.
[5]	BLEI D M, NG A Y, JORDAN M I.Latent Dirichlet Allocation[J]. The Journal of Machine Learning Research,2003,3:993-1022.
[6]	ALLAN J, CARBONELL J G, DODDINGTON G, et al. Topic Detection and Tracking Pilot Study Final Report[EB/OL]. ,2017-7-10.
[7]	单斌, 李芳. 基于LDA话题演化研究方法综述[J]. 中文信息学报, 2010, 24(6):43-49.
[8]	GRIFFITHS T L, STEYYERS M. Finding Scientific Topics.[J]. Proceedings of the National Academy of Sciences of the United States of America, 2004, 101 Suppl 1(1):5228.
[9]	WANG Xuerui, MCCALLUM A.Topics Over Time: A Non-Markov Continuous-time Model of Topical Trends[C]//KDD. 2006 KDD/Proceedings of the Twelfth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 20-23, 2006. Philadelphia, PA, USA. New York: ACM, 2006:424-433.
[10]	ALSUMAIT L, BARBAR D, DOMENICONI C.On-line LDA: Adaptive Topic Models for Mining Text Streams with Applications to Topic Detection and Tracking[C]//IEEE. 2008 ICDM/ Proceedings of the 8th IEEE International Conference on Data Mining, December 15-19, 2008. Pisa, Italy. NJ:IEEE , 2008:3-12.
[11]	WEI Xing, SUN Jimeng, WANG Xuerui.Dynamic Mixture Models for Multiple Time Series[C]// IJCAI. 2007 IJCAI/ Proceedings of the 20th International Joint Conference on Artifical Intelligence, January 6-12, 2007. Hyderabad, India. San Francisco :Morgan Kaufmann Publishers Inc., 2007:2909-2914.
[12]	周玉晶, 沈嘉荟, 邱海韬,等. 基于复杂网络的社交媒体内容安全可视化分析系统[J]. 信息网络安全, 2016(9):158-162.
[13]	BLEI D M, LAFFERTY J D.Dynamic Topic Models[C]//ICML. 2006 ICML/ Proceedings of the 23rd International Conference on Machine Learning, June 25-29, 2006, Pittsburgh, Pennsylvania, USA. New York:ACM, 2006:113-120.
[14]	中华网. 潘基文回国受访表态支持在韩部署“萨德”[EB/OL]. ,2017-7-10.
[15]	周红福, 贾璐, 张婷婷,等. 微博舆情分析中信息转发路径提取方法研究[J]. 信息网络安全, 2016(4):61-68.