Method of bursty events detection based on sentiment filter
FEI Shaodong1,2, YANG Yuzhen3, LIU Peiyu1, WANG Jian4
1. College of Information Science and Engineering, Shandong Normal University, Jinan Shandong 250014, China;
2. Library, Shandong University of Finance and Economics, Jinan Shandong 250014, China;
3. Department of Computer and Information Engineering, Heze University, Heze Shandong 274000, China;
4. School of Science, Shandong University of Technology, Zibo Shandong 255049, China
In we media platform such as microblog, emergency has such characteristics as suddenness and having multiple bursting points. Thus, it brings difficulty to emergency detection. Thus, this paper proposed a method of bursty events detection based on sentiment filter. Firstly, the topic was mapped as a hierarchical model according to the method. Then, dynamic adjustment of the model characteristics was made in a timing-driven way so as to detect the new topics of the information. Based on it, the method analyzed the user's emotional attitude toward such topics. The topics were divided into positive and negative emotion tendencies according to the user's emotional attitude. Additionally, the topic full of negative emotion tendency was regarded as emergent topic. The experimental results show that the accuracy and recall of the proposed method are all increased about 10% compared with baseline.
费绍栋, 杨玉珍, 刘培玉, 王健. 融合情感过滤的突发事件检测方法[J]. 计算机应用, 2015, 35(5): 1320-1323.
FEI Shaodong, YANG Yuzhen, LIU Peiyu, WANG Jian. Method of bursty events detection based on sentiment filter. Journal of Computer Applications, 2015, 35(5): 1320-1323.
[1] KLEINBERG J. Bursty and hierarchical structure in streams[J]. Data Mining and Knowledge Discovery, 2003, 7(4):373-397. [2] FUNG G P C, YU J X, LIU H, et al. Time-dependent event hierarchy construction[C]// Proceedings of the 13th ACM International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2007: 300-309. [3] SUBA I, BERENDT B. From bursty patterns to bursty facts: the effectiveness of temporal text mining for news[C]// Proceedings of the 19th European Conference on Artificial Intelligence. Fairfax: IOS Press, 2010:517-522. [4] VLACHOS N, WU K, CHEN S, et al. Correlating burst events on streaming stock market data[J]. Data Mining and Knowledge Discovery, 2008, 16(1):109-133. [5] TU Y, SENG J. Indices of novelty for emerging topic detection[J]. Information Processing & Management, 2012, 48(2):303-325. [6] XUE F, ZHOU Y, GAO F, et al. An online detection and tracking method for bursty topics[J].Journal of Xi'an Jiaotong University,2011,45(12):64-69.(薛峰,周亚东,高峰,等.一种突发性热点话题在线发现与跟踪方法[J].西安交通大学学报,2011,45(12):64-69.) [7] MANLEY N, KIM Y. Modeling emergency evacuation of individuals with disabilities exit us: an Agent-based public decision support system[J]. Expert Systems with Applications, 2012, 39:8300-8311. [8] YAO J, CUI B, HUANG Y. Bursty event detection from collaborative tags[J]. World Wide Web Internet and Web Information Systems, 2012, 15(2): 171-195. [9] DIAO Q, JIANG J, ZHU F, et al. Finding bursty topics from microblogs [C/OL]. [2012-10-20]. http://max.book118.com. [10] ZHANG L, JIA Y, ZHOU B, et al. Online bursty events detection based on emoticons[J]. Chinese Journal of Computers, 2013,36(8):1659-1667. (张鲁民,贾焰,周斌,等.一种基于情感符号的在线突发事件检测方法[J].计算机学报, 2013,36(8): 1659-1667.) [11] NGUYEN T, PHUNG D, ADAMS B, et al. Event extraction using behaviors of sentiment signals and burst structure in social media[J]. Knowledge and Information Systems, 2013, 37(2):279-304. [12] LAN Y, ZENG R. Research of emergency network public opinion on propagation model and warning phase[J]. Journal of Intelligence,2013,32(5):16-19. (兰月新,曾润喜.突发事件网络舆情传播规律与预警阶段研究[J].情报杂志,2013,32(5):16-19. [13] ALLAN J, PAPKA R, LAVRENKO V. On-line new event detection and tracking[C]// Proceedings of the 21st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 1998:37-45. [14] YANG Y, LIU P, FEI S, et al. A topic link detection method based on improved IB theory[J]. Acta Automatica Sinica, 2014,40(3):471-478. (杨玉珍,刘培玉,费绍栋,等.融合扩展IB理论的话题关联检测方法研究[J]. 自动化学报, 2014,40(3):471-478.) [15] YANG Y, LIU P, FEI S, et al. A method of phrase sentiment analysis based on potential sentiment expectation of context aspects[J]. ICIC Express Letters, 2013,7(10):2855-2860. [16] LEE S, LEE S, KIM K. Bursty event detection from text streams for disaster management[C]// Proceedings of the 21st International Conference Companion on World Wide Web. New York: ACM,2012: 679-682.