Risk assessment of public opinion on extreme rainstorm disasters based on three-way decisions under event system theory

doi:10.16265/j.cnki.issn1003-3033.2025.08.1750

Abstract

Abstract:

In order to realize scientific risk assessment of public opinion on extreme rainstorms, this paper proposed a public opinion risk assessment method of extreme rainstorm disasters based on three-way decisions under the event system theory. From the perspective of event system theory, this method determined the life cycle of public opinion and built indicators for evaluating the risk of public opinion on extreme rainstorm disasters by integrating three dimensions: time, space, and strength. Meanwhile, this paper integrated review helpfulness with hesitant intuitionistic fuzzy sets, effectively quantifying public opinion preferences regarding risk assessment indicators of public opinion. On this basis, the paper extended the three-way decision method to classify public opinion risk into five levels, achieving a scientific assessment of public opinion risk towards extreme rainstorm disasters. Using actual cases and comparative analyses, the effectiveness and adaptability of the risk assessment model of public opinion towards extreme rainstorm disasters were verified. The results show that the proposed method not only successfully realizes the scientific selection of public opinion risk assessment indicators with respect to extreme rainstorm disasters and the effective quantification of public opinion preferences, but also alleviates the decision-making errors caused by the information and cognitive limitations of existing assessment methods to a certain extent.

Key words: event system theory, three-way decisions, extreme rainstorm disasters, public opinion risk assessment, public opinion, review helpfulness

CLC Number:

X915.5

NIE Ruxin, WANG Luo, ZHANG Ziyu. Risk assessment of public opinion on extreme rainstorm disasters based on three-way decisions under event system theory[J]. China Safety Science Journal, 2025, 35(8): 227-235.

Figures/Tables 9

Fig.1

Fig.2

Table 1

Table 2

Table 3

Table 4

Table 5

Table 6

Table 7

References 24

[1]	王晰巍, 李玥琪, 刘婷艳, 等. 新冠肺炎疫情微博用户情感与主题挖掘的协同模型研究[J]. 情报学报, 2021, 40(3): 223-233.
	WANG Xiwei, LI Yueqi, LIU Tingyan, et al. Research on the collaborative model of sentiment analysis and topic mining of micro-blogging users in the context of COVID-19[J]. Journal of the China Society for Scientific and Technical Information, 2021, 40(3): 223-233.
[2]	景楠, 胡怡, 韩喜双. 基于ARIMA与LSTM的新冠肺炎网络关注度趋势研究[J]. 中国安全科学学报, 2020, 30(12): 37-42. doi: 10.16265/j.cnki.issn 1003-3033.2020.12.006
	JING Nan, HU Yi, HAN Xishuang. Trend of COVID-19 network attention based on ARIMA and LSTM[J]. China Safety Science Journal, 2020, 30(12): 37-42. doi: 10.16265/j.cnki.issn 1003-3033.2020.12.006
[3]	晋良海, 王抒情, 王昕煜. 基于暴雨灾害短视频的多模态情感特征研究[J]. 中国安全科学学报, 2024, 34(7): 219-228. doi: 10.16265/j.cnki.issn1003-3033.2024.07.0133
	JIN Lianghai, WANG Shuqing, WANG Xinyu. Research on multimodal emotion characteristics based on short video of rainstorm disaster[J]. China Safety Science Journal, 2024, 34(7): 219-228. doi: 10.16265/j.cnki.issn1003-3033.2024.07.0133
[4]	谢起慧, 席鹏莹, 蔡子庆. 突发事件中多元主体如何生成舆情反转:敏感性、权威度和参与策略[J]. 系统管理学报, 2025, 34(2): 463-476.
	XIE Qihui, XI Pengying, CAI Ziqing. How multiple subjects generate reversal of public opinion in emergencies: sensitivity, authority and participation strategy[J]. Journal of Systems & Management, 2025, 34(2): 463-476.
[5]	王丹, 刘富康, 陆伟. 跨社交媒体舆情风险感知:理论框架的构建与实现[J]. 情报学报, 2024, 43(4): 446-456.
	WANG Dan, LIU Fukang, LU Wei. Cross-social-media public opinion risk perception: construction and implementation of a theoretical framework[J]. Journal of the China Society for Scientific and Technical Information, 2024, 43(4): 446-456.
[6]	刘继, 武梦娇. 基于贝叶斯网络的网络舆情态势评估分析:以“新冠肺炎疫情”事件为例[J]. 情报杂志, 2021, 40(3): 187-192.
	LIU Ji, WU Mengjiao. Assessment and analysis of network public opinion situation based on Bayesian network: COVID-19 as an example[J]. Journal of Intelligence, 2021, 40(3): 187-192.
[7]	谢媛, 李本乾. 新媒体环境下突发环境事件网络舆情风险信息感知模型[J]. 现代情报, 2023, 43(6): 158-165. doi: 10.3969/j.issn.1008-0821.2023.06.016
	XIE Yuan, LI Benqian. Information perception model of network public opinion risk of environmental emergencies in new media environment[J]. Modern Information, 2023, 43(6): 158-165. doi: 10.3969/j.issn.1008-0821.2023.06.016
[8]	杨柳, 罗文倩, 邓春林, 等. 基于灰色关联分析的舆情分级与预警模型研究[J]. 情报科学, 2020, 38(8): 28-34.
	YANG Liu, LUO Wenqian, DENG Chunlin, et al. Classification and early warning model of public opinion based on grey correlation analysis[J]. Information Science, 2020, 38(8): 28-34.
[9]	王华, 罗玲, 乔晶. 网络舆情突发热点事件风险模糊综合评价研究[J]. 情报理论与实践, 2023, 46(11): 126-132.
	WANG Hua, LUO Ling, QIAO Jing. Research on fuzzy comprehensive evaluation of risk of hot events on internet public opinion[J]. Information Studies: Theory & Application, 2023, 46(11): 126-132.
[10]	梁旭东, 夏茹娣, 宝兴华, 等. 2021年7月河南极端暴雨过程概况及多尺度特征初探[J]. 科学通报, 2022, 67(10): 997-1011.
	LIANG Xudong, XIA Rudi, BAO Xinghua, et al. Preliminary investigation on the extreme rainfall event during July 2021 in Henan Province and its multi-scale processes[J]. Chinese Science Bulletin, 2022, 67(10): 997-1011.
[11]	陈睿绮, 李华晶. 基于事件系统理论的绿色农业创业生态系统演化路径研究:以新希望集团为例[J]. 管理学报, 2022, 19(8): 1103-1113.
	CHEN Ruiqi, LI Huajing. Research on the evolution path of green agricultural entrepreneurship ecosystems based on event system theory: take new hope group as an example[J]. Chinese Journal of Management, 2022, 19(8): 1103-1113.
[12]	周欢, 张培颖, 黄晓怡, 等. 事件系统视角下网络舆情态势感知研究[J]. 情报杂志, 2024, 43(2): 135-142.
	ZHOU Huan, ZHANG Peiying, HUANG Xiaoyi, et al. Research on the perception of online public opinion situation from the perspective of event system[J]. Journal of Intelligence, 2024, 43(2): 135-142.
[13]	金笑. 基于在线评论的顾客关键需求识别研究[D]. 徐州: 中国矿业大学, 2021.
	JIN Xiao. Research on Identification of customer key requirements based on online reviews[D]. Xuzhou: China University of Mining and Technology, 2021.
[14]	TIAN Zhangpeng, LIANG Heming, NIE Ruxin, et al. Data-driven multi-criteria decision support method for electric vehicle selection[J]. Computers & Industrial Engineering, 2023, 177: DOI:10.1016/j.cie.2023.109061.
[15]	徐健锋, 何宇凡, 汤涛, 等. 概率粗糙集三支决策在线快速计算算法研究[J]. 智能系统学报, 2018, 13(5): 741-750.
	XU Jianfeng, HE Yufan, TANG Tao, et al. Research on a fast online computing algorithm based on three-way decisions with probabilistic rough sets[J]. CAAI Transactions on Intelligent Systems, 2018, 13(5): 741-750.
[16]	杜俊良, 刘思峰, 刘勇, 等. 基于三支决策的灰色可能度聚类方法及应用[J]. 运筹与管理, 2024, 33(1): 23-28. doi: 10.12005/orms.2024.0004
	DU Junliang, LIU Sifeng, LIU Yong, et al. Three-way decision based grey possibility clustering approach and its application[J]. Operations Research and Management Science, 2024, 33(1): 23-28. doi: 10.12005/orms.2024.0004
[17]	汤国林, 杨文栋, 刘培德. 基于区间二型模糊决策粗糙集的三支决策方法[J]. 控制与决策, 2022, 37(5): 1347-1356.
	TANG Guolin, YANG Wendong, LIU Peide. Three-way decisions based on decision-theoretic rough sets with interval type-2 fuzzy information[J]. Control and Decision, 2022, 37(5): 1347-1356.
[18]	ZHANG Xianyong, CHEN Jiang. Three-way quantitative models and three-way issue reductions of conflict analysis[J]. Information Sciences, 2025, 701: DOI:10.1016/j.ins.2024.121846.
[19]	JIA Fan, LIU Peide. A novel three-way decision model under multiple-criteria environment[J]. Information Sciences, 2019, 471: 29-51. doi: 10.1016/j.ins.2018.08.051
[20]	河南郑州“7·20”特大暴雨灾害调查报告公布[EB/OL]. (2022-01-21). http://www.news.cn/2022-01/21/c_1128287291.htm.
[21]	SHANNON C. A mathematical theory of communication[J]. Bell System Technical Journal, 1948, 5(1): 3-55.
[22]	刘逸伦, 黄微, 卢国强. 基于AHPSortⅡ的突发事件网络舆情群体极化风险评估研究[J]. 现代情报, 2024, 44(5): 107-122.
	LIU Yilun, HUANG Wei, LU Guoqiang. Research on group polarization risk assessment of network public opinion in emergencies[J]. Journal of Modern Information, 2024, 44(5): 107-122.
[23]	江长斌, 徐紫琪, 王宏宇, 等. 基于熵权TOPSIS法的高校师德师风类网络舆情风险评估预警研究[J]. 情报科学, 2024, 42(6): 113-120.
	JIANG Changbin, XU Ziqi, WANG Hongyu, et al. Risk assessment and early warning of network public opinion related to the ethics and conduct of university faculty based on entropy weight TOPSIS method[J]. Information Science, 2024, 42(6): 113-120.
[24]	武慧娟, 张海涛, 王尽晖, 等. 基于熵权法的网络舆情预警模糊综合评价模型研究[J]. 情报科学, 2018, 36(7): 58-61.
	WU Huijuan, ZHANG Haitao, WANG Jinhui, et al. Research on the fuzzy comprehensive evaluation model of online public opinion pre-warning based on entropy weight method[J]. Information Science, 2018, 36(7): 58-61.

风险等级	(u_A,v_A)	记分函数 ${S}_{A}={\mu }_{A}-{v}_{A}$
低	(0,1)	-1
较低	(0.25,0.75)	-0.5
中	(0.5,0.5)	0
较高	(0.75,0.25)	0.5
高	(1,0)	1

二级指标	三级指标	指标解释
情感强度	暴雨描述	关于暴雨本身相关信息的情感分布
	热点事件	关于暴雨整个事件过程中发生的热点事件的情感分布
	救援情况	民众对各方救援情况的情感分布
	政府部门应对情况	民众对于政府部门应急处置的情感分布
	祝愿祈祷	民众面对灾害时祈求平安的情感分布
	基础设施	民众对于基础设施的破坏,修缮等情况的情感分布
空间扩散效果	微博总量	一定时间段内的话题相关的微博总量
	转发总量	一定时间段内相关微博的转发总量
	点赞总量	一定时间段内相关微博的点赞总量
事件原发属性	财产损失	反映因暴雨灾害造成的直接经济损失情况
	受灾人口	受到暴雨灾害影响的伤亡人口和灾害直接造成生产生活出现一定损害的人口数量
	灾害等级	按照自然灾害的重大程度从重到轻分为I、Ⅱ、Ⅲ、Ⅳ这4个等级

三级指标	日期	微博总量	转发总量	点赞总量	财产损失	受灾人口	防汛响应等级
潜伏期	7月1日—21日	126	217 768	782 363	0	0	未响应
形成期	7月22日—25日	45 684	524 333	4 194 661	532亿元	1 453.1万	I级
波动期	7月26日—8月26日	21 268	463 161	4 070 007	668.6亿元	1478.6万	Ⅱ级
消退期	8月26日—31日	2 153	16 788	117 950	300.1亿元	732.94万	Ⅳ级

时期	主题1		主题2		主题3		主题4		主题5		主题6
时期	得分	权重	得分	权重	得分	权重	得分	权重	得分	权重	得分	权重
潜伏期	0.341	0.095	0.654	0.067	0.456	0.171	0.222	0.076	0.309	0.055	0.848	0.117
爆发期	0.308	0.791	0.412	0.889	0.314	0.669	0.375	0.764	0.428	0.896	0.779	0.624
波动期	0.385	0.066	0.439	0.027	0.285	0.139	0.337	0.075	0.527	0.035	0.707	0.227
消退期	0.460	0.048	0.535	0.017	0.658	0.021	0.523	0.085	0.394	0.014	0.739	0.032
加权得分	0.325		0.432		0.339		0.350		0.413		0.753

指标	评价结果	未加权得分	加权得分
微博总量	{(0,1),(1,0),(1,0),(0.5,0.5)}	0.25	0.770
转发总量	{(0.5,0.5),(1,0),(1,0),(0,1)}	0.25	0.831
点赞总量	{(0.5,0.5),(1,0),(1,0),(0.75,0.25)}	0.625	0.885
财产损失	{(0,1),(1,0),(1,0),(0.75,0.25)}	0.375	0.788
受灾人口	{(0,1),(1,0),(1,0),(0.75,0.25)}	0.375	0.788
防汛响应等级	{(0,1),(1,0),(0.75,0.25),(0.25,0.75)}	0	0.705