突发公共卫生事件网络谣言网格化预警模型研究

doi:10.16381/j.cnki.issn1003-207x.2021.1501

Abstract

Abstract:

In order to improve the problem of low efficiency and insufficient reliability of online rumors early warning， a grid-based early warning model for online rumors of public health emergencies is established. Firstly， the depth of confusion of online rumors to individual audience is identified longitudinally by quantifying the basic characteristics of online rumors based on the grey-weighted correlation analysis. Secondly， the spread of online rumors to audience groups is predicted horizontally combined the dynamic game of incomplete information with simulation. Finally， the assessment results of both vertical and horizontal dimensions are integrated to define the overall social influence of online rumors， and a visual four-level early warning classification for mild， warning， severe，and danger is carried out， and four emergency management and control strategies of delay， suppression， confronation and suppression are correspondingly proposed. The case of “Shuanghuanglian” is taken as an example to verify the effectiveness of the online rumors grid-based early warning model and its choke tactics. In terms of theoretical research value， it is the first time that the dual perspectives of “identification-warning” and “dissemination-warning” are combined to predict the early-warning level of the overall social influence of online rumors. Based on the interaction between information and audience， the information vagueness of online rumor is estimated more comprehensively， and both the individual cognitive judgment of the audience and the game psychology of the audience group are considered in the evaluation of the spread of online rumors. At the same time， the whole process of this study relies on big data， artificial intelligence and other automatic technologies to improve the objectivity of the evaluation of social influence of online rumors. On the basis of visualizing the four-level warning （mild level， warning level， severe level and danger level） of the overall social influence of online rumors， four emergency management and control strategies are proposed respectively， which promoted the study of online rumors governance.

Key words: public health emergencies, online rumors, early warning model, grey-weighted correlation analysis, dynamic game with incomplete information

CLC Number:

G202

Guirong Zhang,Zhixiang Dong,Ting Xia. Study on the Grid-based Early Warning Model for Online Rumors of Public Health Emergencies[J]. Chinese Journal of Management Science, 2024, 32(2): 298-306.

Figures/Tables 9

References 18

1	张鹏，兰月新，李昊青，等. 基于HAYASHI数量化理论的网络谣言分类应对策略分析［J］. 情报杂志， 2016， 35（1）： 110-115.
	Zhang P， Lan Y X， Li H Q， et al. Analysis of internet rumors classification based on hayshi quantificationtheory［J］. Journal of Intelligence， 2016， 35（1）： 110-115.
2	王征，叶长安. 微博谣言识别与预警算法研究［J］. 情报杂志， 2019， 38（4）： 148-154.
	Wang Z， Ye C A. Micro-blog gossip recognition and early warning algorithm research based on complex networks［J］.Journal of Intelligence， 2019，38（4）： 148-154.
3	Wang L， Liu F M， Yang R R. Researchon rumor early warning mechanism based on kinetic energy［C］//Proceedings of the 2015 4th National Conference on Electrical， Electronics and Computer Engineering， Xi’an China， December 12-13 ，Atlantis Press，2015： 382-388.
4	吴文汐，荣雪，李成博. 智能媒体环境下谣言的识别、控制与更正——基于算法与用户心理的考察［J］. 传媒， 2019，（12）： 18-19+21.
	Wu W X， Rong X， Li C B. Therecognition， control and correction of rumors in the smart media environment： based on the investigation of algorithmsand user psychology［J］. Media， 2019（12）： 18-19+21.
5	张鹏，兰月新，李昊青，等. 突发事件网络谣言危机预警及模拟仿真研究［J］. 现代情报， 2019， 39（12）： 101-108+137.
	Zhang P， Lan Y X， Li H Q， et al. Study on the simulation and crisis early-warning of internet rumors about emergencies［J］. Journal of Modern Information， 2019， 39（12）： 101-108+137.
6	戎蕊，兰月新，戴艳梅，等. 网络谣言影响力因素评价体系及策略研究［J］. 现代情报， 2014， 34（10）： 25-30.
	Rong R， Lan Y X， Dai Y M， et al. Study on evaluation system and strategies of influence factors of network rumors［J］.Journal of Modern Information， 2014， 34（10）： 25-30.
7	张鹏，李昊青，兰月新，等. 基于BP神经网络的突发事件网络谣言危机预警［J］. 电子政务， 2016，（11）： 40-47.
	Zhang P， Li H Q， Lan Y X， et al. Emergency network rumor crisis warning based on BP neural network［J］. E-Government， 2016（11）： 40-47.
8	曹蓉. 基于全样本分析的网络舆情指标体系研究综述［J］. 情报杂志， 2015， 34（5）： 154-158+28.
	Cao R. Full-sample based literaturereview on the study of network public opinion index systems［J］. Journal of Intelligence， 2015， 34（5）： 154-158+28.
9	魏阳，张鹏，兰月新，等.基于灰色关联分析的网络谣言识别方法研究［J］.情报杂志， 2017， 36（12）： 119-125.
	Wei Y， Zhang P， Lan Y X， et al. Research on internet rumors identification method based on grey relational theory［J］. Journal of Intelligence， 2017， 36（12）： 119-125.
10	Allport G W， Postman L. The psychology of rumor［M］. New York： Henry Holt and Company， 1947.
11	Castillo C， Mendoza M， Poblete B. Information credibility on twitter［C］//Proceedings of the 20th International Conference on World Wide Web， Hyderabad， India， March 28， 2011.
12	Qazvinlian V， Rosengren E， Radev D R， et al. Rumor has it identifying misinformation in microblogs［C］//Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing， Edinburgh， UK， July 2011： 27-31.
13	Nadamoto A， Miyabe M， Aramaki E. Analysis of microblog rumors and correction texts for disaster situations［C］//Proceedings of the International Conference on Information Integration & Web-based Applications & Services， Kobe， Japan， December 2， 2013.
14	贺刚，吕学强，李卓，等. 微博谣言识别研究［J］. 图书情报工作， 2013， 57（23）： 114-120.
	He G， Lv X Q， Li Z， et al. Automatic rumor identification on micro-blog［J］. Library and Information Service， 2013， 57（23）： 114-120.
15	张芳，司光亚，罗批. 基于演化博弈理论的人际谣言传播仿真模型研究［J］. 系统仿真学报， 2011， 23（9）： 1772-1775.
	Zhang F， Si G Y， Luo P. Study on rumor spreading model based on evolution game［J］. Journal of System Simulation， 2011， 23（9）： 1772-1775.
16	张桂蓉，夏霆. 突发公共事件网络谣言传播长尾效应的控制研究——以新型冠状病毒肺炎疫情为例［J］. 情报理论与实践， 2021， 44（3）： 69-75.
	Zhang G R， Xia T. Research on the control of the long-tail effect of internet rumor spread in public health emergencies： taking the coronavirus disease 2019 pandemic as an example［J］. Information Studies： Theory & Application， 2021， 44（3）： 69-75.
17	马续补，陈颖，秦春秀. 突发公共卫生事件科研信息报道的网络舆情特征分析及应对策略［J］. 现代情报， 2020， 40（10）： 3-10+61.
	Ma X B， Chen Y， Qin C X. Research on the characteristics of online public opinion for scientific research information reporting in public health emergencies and its coping strategies［J］. Journal of Modern Information， 2020， 40（10）： 3-10+61.
18	田世海，王春梦，杨文蕊. 基于ANP和随机Petri网的突发事件网络舆情危机预警机制研究［J］. 中国管理科学， 2023， 31（10）： 215-224.
	Tian S H， Wang C M， Yang W R. Research on the early warning mechanism of network public opinion crisis for emergencies based on ANP and stochastic petri net［J］. Chinese Journal of Management Science， 2023， 31（10）： 215-224.

一级特征	二级特征	量化赋值
用户特征	微博发布主体属性	个人赋值1，新闻媒体赋值2，政府部门赋值3
	粉丝数及关注数	不足1千人赋值1，1千-2千人赋值2，2千-5千人赋值3，5千-1万赋值4，超过1万人赋值5
	是否为验证用户	非验证用户赋值1，验证用户赋值2
结构特征	微博的叙事结构	快转赋值1，转发评论赋值2
	微博内容总长度	评论字数在1-28区间赋值1，评论字数在29-56区间赋值2，评论字数在57-84区间赋值3，评论字数在85-112区间赋值4，评论字数在113-140区间赋值5
	微博的承载形式	内容为纯文字1，包含涉事图片赋值2，包含涉事视频赋值3
	微博的原创性讨论数	不足1千人赋值1，1千-5千人赋值2，5千-2万人赋值3，2万-10万人赋值4，超过10万人赋值5
传播特征	微博的转发次数	不足1千人赋值1，1千-5千人赋值2，5千-2万人赋值3，2万-10万人赋值4，超过10万人赋值5
	微博的评论次数	不足1千人赋值1，1千-5千人赋值2，5千-2万人赋值3，2万-10万人赋值4，超过10万人赋值5
	微博的多次传播	不含@符号赋值1，含有@符号赋值2
情感特征	公众情绪分布	各情绪分布划分情况
情感特征	公众情绪强度	记录各类情绪所占比例大小

	用户特征	结构特征	传播特征	情感特征	权重
用户特征	1	1/2	5	5	0.3953
结构特征	2	1	4	1/9	0.1936
传播特征	1/7	1/4	1	1/2	0.0560
情感特征	1/5	9	2	1	0.3551

[1]	ZHU Hong-miao, YAN Xin, QI Jia-yin, JIN Zhen. Research on Communication Model and Intervention Strategy of COVID-19 Vaccination Consciousness Among Public [J]. Chinese Journal of Management Science, 2023, 31(8): 269-277.
[2]	WEN Feng-hua, SHEN Ti-yan, XING Jiang-bo, KOU Chen-huan. Urban Evidence-based Governance Mechanism of Public Health Emergencies [J]. Chinese Journal of Management Science, 2023, 31(1): 206-215.

Study on the Grid-based Early Warning Model for Online Rumors of Public Health Emergencies

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 9

References 18

Related Articles 2

Metrics

Comments

Recommended 0