广东工业大学学报 ›› 2022, Vol. 39 ›› Issue (03): 32-40,48.doi: 10.12052/gdutxb.210202

• • 上一篇    下一篇

融合立场检测和主题挖掘的突发公共事件网络舆情演化研究

刘高勇, 黄靖钊, 艾丹祥   

  1. 广东工业大学 管理学院, 广东 广州 510520
  • 收稿日期:2021-12-22 出版日期:2022-05-10 发布日期:2022-05-19
  • 通信作者: 艾丹祥(1978-),女,副教授,博士,主要研究方向为知识工程、文本挖掘,E-mail:aidx@gdut.edu.cn
  • 作者简介:刘高勇(1975-)，男，教授，博士，主要研究方向为大数据分析、智能信息处理
  • 基金资助:
    广东省哲学社会科学“十三五”规划项目(GD20CTS01)；广州市哲学社会科学发展“十三五”规划项目(2018GZYB67)

A Research on Online Public Opinion Evolution of Public Emergencies Based on Stance Detection and Topic Mining

Liu Gao-yong, Huang Jing-zhao, Ai Dan-xiang   

  1. School of Management, Guangdong University of Technology, Guangzhou 510520, China
  • Received:2021-12-22 Online:2022-05-10 Published:2022-05-19

HTML

PDF (PC)

2464

摘要： 基于立场检测和主题挖掘的突发公共事件舆情演化研究，能够帮助政府及利益相关者快速地掌握突发公共事件网络舆情的演化规律，具有重要的意义。划分具体突发公共事件的舆情生命周期，提出新的立场检测模型和主题句挖掘方法，针对每个生命周期阶段，在识别大众网民的立场信息的基础上筛选出高效用的舆情信息，再挖掘高效用舆情信息的主题，以深入分析突发公共事件主题信息的演化规律。以“杭州女子失踪案”的微博数据为例，首先将本文方法与多种方法的实验结果进行对比分析，验证了方法的有效性；然后基于实验结果进行舆情演化分析，证明了其能够在实际的突发公共事件舆情中快速聚焦关键点，较好地分析突发公共事件舆情演化规律和特点。该方法能较有效、准确地识别和分析舆情内容，为网络舆情演化的研究提供了新视角。

关键词: 立场检测, 主题挖掘, 突发公共事件, 舆情演化

Abstract: The research on the evolution of public opinions in public emergencies based on stance detection and topic mining can help the government and stakeholders quickly grasp the evolution law of online public opinions in public emergencies, which is of great significance. The public opinion life cycle of specific public emergencies is divided, and a new stance detection model and a topic sentence mining method are proposed. For each life cycle stage, on the basis of identifying the stance information of mass Internet users, the efficient public opinion information is screened out, and then the topics of efficient public opinion information are mined, so as to deeply analyze the evolution law of the topic information of public emergencies. Taking the microblog data of "A Hangzhou Woman Missing Case" as an example, firstly, the experimental results of this method and various methods are compared to verify the effectiveness of this method.Then, the evolution of public opinions is analyzed based on the experimental results of this method, which proves that this method can quickly focus on the key points in the actual public opinions of public emergencies, and better analyze the evolution law and characteristics of public opinions of public emergencies. This method can effectively and accurately identify and analyze the content of public opinions, and provide a new perspective for the study of the evolution of network public opinions.

Key words: stance detection, topic mining, public emergency, evolution of public opinion

中图分类号: 

  • C916
[1] 中国法制出版社. 中华人民共和国突发事件应对法: 实用版[M]. 北京: 中国法制出版社, 2010.
[2] MOHAMMAD S, KIRITCHENKO S, SOBHANI P, et al. SemEval-2016 task 6: detecting stance in Tweets[C]// ZHU X D. Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016). Stroudsburg: ACL, 2016: 31-41.
[3] SRIDHAR D, GETOOR L, WALKER M . Collective stance classification of posts in online debate forums[C]// GETOOR L. Proceedings of the Joint Workshop on Social Dynamics and Personal Attributes in Social Media. Maryland: Association for Computational Linguistics, 2014: 109-117.
[4] WALKER M A, ANAND P, ABBOTT R, et al. Stance classification using dialogic properties of persuasion[C]// ANAND P. Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Montreal: Association for Computational Linguistics, 2012: 592-596.
[5] XU R, ZHOU Y, WU D, et al. Overview of NLPCC shared task 4: stance detection in Chinese microblogs[C]// LIN C Y. NLPCC-ICCPOL 2016. Switzerland: Springer International Publishing, 2016: 907-916.
[6] 奠雨洁, 金琴, 吴慧敏. 基于多文本特征融合的中文微博的立场检测[J]. 计算机工程与应用, 2017, 53(21): 77-84.
DIAN Y J, JIN Q, WU H M. Stance detection in Chinese microblogs via fusing multiple text features [J]. Computer Engineering and Application, 2017, 53(21): 77-84.
[7] MOHAMMAD S M, SOBHANI P, KIRITCHENKO S. Stance and sentiment in Tweets [J]. ACM Transactions on Internet Technology, 2017, 17(3): 23.
[8] KAZUAKI H, AKIRA S, NAOAKI O, et al. Stance detection attending external knowledge from Wikipedia [J]. Journal of Information Processing, 2019, 27: 499-506.
[9] 白静, 李霏, 姬东鸿. 基于注意力的Bi-LSTM-CNN中文微博立场检测模型[J]. 计算机应用与软件, 2018(3): 266-274.
BAI J, LI F, JI D H. Attention based Bi-LSTM-CNN Chinese microblogging position detection model [J]. Computer Applications and Software, 2018(3): 266-274.
[10] 周艳芳, 周刚, 鹿忠磊. 一种基于迁移学习及多表征的微博立场分析方法[J]. 计算机科学, 2017, 45(9): 243-247.
ZHOU Y F, ZHOU G, LU Z L. Approach of stance detection in micro-blog based on transfer learning and multi-representation [J]. Computer Science, 2017, 45(9): 243-247.
[11] MIKOLOV T, SUTSKEVER I, CHEN K, et al. Distributed representations of words and phrases and their compositionality[EB/OL]. (2013-10-16)[2020-01-19]. https://arxiv.org/pdf/1310.4546.pdf.
[12] LUHN H P. A statistical approach to mechanized encoding and searching of literary information [J]. IBM Journal of Research and Development, 1957, 1(4): 309-317.
[13] WEI W, GUO C. A text semantic topic discovery method based on the conditional co-occurrence degree [J]. Neurocomputing, 2019, 368(27): 11-24.
[14] 安璐, 胡俊阳, 李纲. 基于主题一致性和情感支持的评论意见领袖识别方法研究[J]. 管理科学, 2019, 32(1): 1-13.
AN L, HU J Y, LI G. A method of identifying comment opinion leaders based on topic consistency and emotional support [J]. Journal of Management Science, 2019, 32(1): 1-13.
[15] 李跃鹏, 金翠, 及俊川. 基于word2vec的关键词提取算法[J]. 科研信息化技术与应用, 2015(4): 54-59.
LI Y P, JIN C, JI J C. A keyword extraction algorithm based on word2vec[J]. E-science Technology and Application, 2015(4): 54-59.
[16] 孔胜, 王宇. 基于句子相似度的文本主题句提取算法研究[J]. 情报学报, 2011, 30(6): 605-609.
KONG S, WANG Y. Topic sentences extraction method based on sentence similarity [J]. Journal of the China Society for Scientific and Technical Information, 2011, 30(6): 605-609.
[17] 唐晓波, 肖璐. 基于单句粒度的微博主题挖掘研究[J]. 情报学报, 2014(33): 632.
TANG X B, XIAO L. Research of micro-blog topics mining based on sentence granularity [J]. Journal of the China Society for Scientific and Technical Information, 2014(33): 632.
[18] 万国, 张桂平, 白宇, 等. 基于特征加权的新闻主题句抽取[J]. 中文信息学报, 2017, 31(5): 120-126.
WAN G, ZHANG G P, BAI Y, et al. News topic sentence extraction via weighted features [J]. Journal of Chinese Information Processing, 2017, 31(5): 120-126.
[19] 杜洪涛, 王君泽, 李婕. 基于多案例的突发事件网络舆情演化模式研究[J]. 情报学报, 2017, 10(10): 1038-1049.
DU H T, WANG J Z, LI J. Research on evolution model for online public opinion of emergent events based on multiple cases [J]. Journal of the China Society for Scientific and Technical Information, 2017, 10(10): 1038-1049.
[20] FINK S. Crisis management: planning for the inevitable [M]. New York: American Management Association, 1986.
[21] 贾亚敏, 安璐, 李纲. 城市突发事件网络信息传播时序变化规律研究[J]. 情报杂志, 2015(4): 94-100.
JIA Y M, AN L, LI G. On the online information dissemination pattern of city emergencies [J]. Journal of Intelligence, 2015(4): 94-100.
[22] 王曰芬, 王一山, 杨洁. 基于社区发现和关键节点识别的网络舆情主题发现与实证分析[J]. 图书与情报, 2020(5): 48-58.
WANG Y F, WANG Y S, YANG J. Topic discovery and empirical analysis of network public opinion based on community detection and key node identification [J]. Library and Information, 2020(5): 48-58.
No related articles found!
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2017 《广东工业大学学报》编辑部
地址：广州市东风东路729号广东工业大学 邮编：510090
电话：020-37626653,020-37626139,020-37626396
邮箱：xbzrb@gdut.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发