融合情感过滤的突发事件检测方法

doi:10.11772/j.issn.1001-9081.2015.05.1320

计算机应用 ›› 2015, Vol. 35 ›› Issue (5): 1320-1323.DOI: 10.11772/j.issn.1001-9081.2015.05.1320

融合情感过滤的突发事件检测方法

费绍栋^1,2, 杨玉珍³, 刘培玉¹, 王健⁴

1. 山东师范大学信息科学与工程学院, 济南 250014;
2. 山东财经大学图书馆, 济南 250014;
3. 菏泽学院计算机与信息工程系, 山东菏泽 274000;
4. 山东理工大学理学院, 山东淄博 255049

收稿日期:2014-12-17 修回日期:2015-01-29 出版日期:2015-05-10 发布日期:2015-05-14
通讯作者: 杨玉珍
作者简介:费绍栋(1984-),男,山东济南人,讲师,博士研究生,主要研究方向:网络舆情分析、中文倾向性分析; 杨玉珍(1978-),女,山东菏泽人,讲师,博士,主要研究方向:网络信息安全、倾向性分析; 刘培玉(1960-),男,山东临朐人,教授,博士生导师,CCF高级会员,主要研究方向:网络信息安全、自然语言处理; 王健(1963-),男,山东淄博人,副教授,主要研究方向:机器学习.
基金资助:
国家自然科学基金资助项目(61373148);国家社会科学基金资助项目(12BXW040);山东省自然科学基金资助项目(ZR2012FM038);山东省优秀中青年科学家奖励基金资助项目(BS2013DX033);山东省自然科学基金资助项目(ZR2014FL010);教育部人文社会科学基金资助项目(14YJC860042).

Method of bursty events detection based on sentiment filter

FEI Shaodong^1,2, 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

Received:2014-12-17 Revised:2015-01-29 Online:2015-05-10 Published:2015-05-14

摘要/Abstract

摘要：

针对微博等自媒体平台中,突发事件存在的突发性、多爆发点,给突发事件检测带来困难,提出一种整合用户情感过滤的突发事件检测方法.该方法首先将话题映射为层次模型,以时序驱动的方式动态调整模型特征,探测信息新话题.以此为基础分析用户对该话题所持有的情感态度,依据用户的情感态度将话题划分为正面和负面情感倾向两类,并将饱含负面情感倾向的话题视为突发话题.实验证明,无论是准确率还是查全率所提方法均比baseline提高约10%以上.

关键词: 突发事件检测, 情感倾向, 情感过滤, 自然语言处理, 信息碎片化

Abstract:

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.

Key words: bursty events detection, sentiment orientation, sentiment filter, Natural Language Processing (NLP), fragmentation of information

中图分类号:

TP391

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[J]. Journal of Computer Applications, 2015, 35(5): 1320-1323.

参考文献

[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.

融合情感过滤的突发事件检测方法

Method of bursty events detection based on sentiment filter

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	谢德峰, 吉建民. 融入句法感知表示进行句法增强的语义解析[J]. 计算机应用, 2021, 41(9): 2489-2495.
[2]	刘雅璇, 钟勇. 基于头实体注意力的实体关系联合抽取方法[J]. 计算机应用, 2021, 41(9): 2517-2522.
[3]	周险兵, 樊小超, 任鸽, 杨勇. 基于多层次语义特征的英文作文自动评分方法[J]. 计算机应用, 2021, 41(8): 2205-2211.
[4]	李文惠, 曾上游, 王金金. 基于改进注意力机制的图像描述生成算法[J]. 计算机应用, 2021, 41(5): 1262-1267.
[5]	刘睿珩, 叶霞, 岳增营. 面向自然语言处理任务的预训练模型综述[J]. 计算机应用, 2021, 41(5): 1236-1246.
[6]	王朱君, 王石, 李雪晴, 朱俊武. 基于深度学习的事件因果关系抽取综述[J]. 计算机应用, 2021, 41(5): 1247-1255.
[7]	李雪晴, 王石, 王朱君, 朱俊武. 自然语言生成综述[J]. 计算机应用, 2021, 41(5): 1227-1235.
[8]	杨璐, 何明祥. 基于门控机制和卷积神经网络的中文文本情感分析模型[J]. 计算机应用, 2021, 41(10): 2842-2848.
[9]	杨国峰, 杨勇. 基于BERT的常见作物病害问答系统问句分类[J]. 计算机应用, 2020, 40(6): 1580-1586.
[10]	赵亚欧, 张家重, 李贻斌, 付宪瑞, 生伟. 融合基于语言模型的词嵌入和多尺度卷积神经网络的情感分析[J]. 计算机应用, 2020, 40(3): 651-657.
[11]	黄友文, 游亚东, 赵朋. 融合卷积注意力机制的图像描述生成模型[J]. 计算机应用, 2020, 40(1): 23-27.
[12]	陈志豪, 余翔, 刘子辰, 邱大伟, 顾本刚. 基于注意力和字嵌入的中文医疗问答匹配方法[J]. 计算机应用, 2019, 39(6): 1639-1645.
[13]	严红, 陈兴蜀, 王文贤, 王海舟, 殷明勇. 基于深度神经网络的法语命名实体识别模型[J]. 计算机应用, 2019, 39(5): 1288-1292.
[14]	张克君, 李伟男, 钱榕, 史泰猛, 焦萌. 基于深度学习的文本自动摘要方案[J]. 计算机应用, 2019, 39(2): 311-315.
[15]	王雪颖, 杨文忠, 张志豪, 李东昊, 秦旭. 基于多特征的微博突发事件检测算法[J]. 计算机应用, 2019, 39(11): 3263-3267.