公众诉求回应政策的微博用户讨论热度演变机制研究

doi:10.16381/j.cnki.issn1003-207x.2025.0498

Abstract

Abstract:

In the new media era， policies responding to public demands can be disseminated to the public immediately， yet they require time to be implemented and demonstrate effectiveness. Research on the evolution mechanism of public discussion heat regarding related topics aids administrative departments in assessing public opinion trends and guiding discussion heat proactively and appropriately.When Weibo users become aware of government-published policies addressing public demands， their desire for immediate gratification motivates them to expect prompt benefits from these policies. Concurrently， users possess self-regulation capabilities， which exert a counteracting influence on their immediate gratification impulses. Additionally， users tend to forget previously viewed content， thereby influencing their online browsing behaviors and relational dynamics.Weibo users are categorized into four groups： Unknowns， Followers， Communicators， and Silencers. By incorporating the psychological factors of immediate gratification and self-regulation， transition functions between these groups are established， forming a dissemination model based on immediate gratification and self-regulation.The dataset comprised 119，057 Weibo comments from 90，705 users under relevant topics on the Sina Weibo platform during the implementation of the “Nine Prohibitions” policy. Genetic algorithms are subsequently employed to fit the model parameters， reconstructing the temporal evolution curve of user participation in related discussions.Finally， the impact of parameters on the scale and growth rate of discussion heat is analyzed from two dimensions： information dissemination pathways and user psychology. The effects of four moderation strategies on discussion heat are evaluated. Findings indicate that the model effectively explains the evolutionary trend of potential maximum discussion heat among Weibo users. Measures such as labeling misinformation on social media platforms and promptly responding to public demands demonstrate relatively superior moderation efficacy. Future research could integrate additional psychological theories to better characterize the evolution of online public opinion.

Key words: appeal response policy, weibo user discussion heat, IGSA-UFCS model, emergency management

CLC Number:

C393

Longtao Qin,Jiayi Huang,Mingliang Qi. Research on the Evolution Mechanism of Weibo User Discussion Heat for Public Demand Response Policies——A Case Based on Weibo Users Data[J]. Chinese Journal of Management Science, 2026, 34(11): 130-141.

Figures/Tables 17

参数类型	参数符号	参数含义
基本参数	n	总用户数
基本参数	UN_t、FN_t、CN_t、SN_t	在t时刻未知者、关注者、传播者、沉默者的用户数量
基本参数	U_t、F_t、C_t、S_t	在t时刻未知者、关注者、传播者、沉默者的用户集合
基本参数	e	自然数e
基本参数	t	当前时间步，表示政策发布后第t天
基本参数	Forget	遗忘率，表示用户遗忘各条已阅读微博评论的概率
基本参数	PS_t	t时刻未知者的网络关系中有传播者的比例
基本参数	PS_it	t时刻未知者i的网络关系中是否有传播者的状态值
舆情传播途径参数	α	未知者对于相关话题不感兴趣的概率
舆情传播途径参数	β	关注者对于相关话题不感兴趣的概率
舆情传播途径参数	γ	传播者对于相关话题不感兴趣的概率
舆情传播途径参数	θ	沉默者对于相关话题感兴趣的概率
舆情传播途径参数	σ	关注者和传播者受他人影响，参与传播的概率
舆情传播途径参数	m	各类人群每次浏览的微博评论数
即时满足心理参数	IR_t	t时刻关注者和传播者的平均即时满足心理强度
即时满足心理参数	IR_it	t时刻关注者或传播者i在知晓相关话题信息后，出于即时满足心理，参与话题传播的概率
即时满足心理参数	IR_i0	表示i用户的初始即时满足心理强度，服从正态分布
即时满足心理参数	IR_t_i	表示i用户第一阶段即时满足心理持续时间，服从正态分布
即时满足心理参数	p	用户受即时满足心理影响，浏览微博评论内容的概率
即时满足心理参数	D	即时满足心理对时间的敏感度
自我调节参数	AR_i	用户i的自我调节能力阈值集合，描述用户基于此能力对其他用户影响和自身心理的调节能力，服从正态分布
自我调节参数	AR_t_i	用户i自我调节的最长时间范围，服从正态分布
自我调节参数	B	自我调节效率
自我调节参数	E	自我调节准备时间
自我调节参数	LT_i	用户i不再进行自我调节的开始时间
自我调节参数	T_inf_ti	t时刻用户i受到的总影响量
自我调节参数	inf_ti	t时刻用户i受到相邻节点的影响量

References 30

[1]	宋亮，周洪林. 网民介入公共政策传播的路径及其风险规避［J］. 新闻世界， 2016（8）： 34-39.
	Song L， Zhou H L. The path of netizens' involvement in the dissemination of public policies and its risk avoidance［J］. News World， 2016（8）： 34-39.
[2]	Li S， Liu Z， Li Y. Temporal and spatial evolution of online public sentiment on emergencies［J］. Information Processing & Management， 2020， 57（2）： 102177.
[3]	王晰巍，贾若男，韦雅楠，等. 多维度社交网络舆情用户群体聚类分析方法研究［J］. 数据分析与知识发现， 2021， 5（6）： 25-35.
	Wang X W， Jia R N， Wei Y N， et al. Clustering user groups of public opinion events from multi-dimensional social network［J］. Data Analysis and Knowledge Discovery， 2021， 5（6）： 25-35.
[4]	郑石明，兰雨潇，黎枫. 网络公共舆论与政府回应的互动逻辑——基于新冠肺炎疫情期间“领导留言板”的数据分析［J］. 公共管理学报，2021， 18（3）： 24-37+169.
	Zheng S M， Lan Y X， Li F. The interactive logic of online public opinion and government response—Based on the data analysis of the “leadership message board” during the COVID-19 pandemic［J］. Journal of Public Management， 2021， 18（3）： 24-37+169.
[5]	丁学君. 基于SCIR的微博舆情话题传播模型研究［J］. 计算机工程与应用， 2015， 51（8）： 20-26+78.
	Ding X J. Research on propagation model of public opinion topics based on SCIR in microblogging［J］. Computer Engineering and Applications， 2015， 51（8）： 20-26+78.
[6]	Suo S， Chen Y. The dynamics of public opinion in complex networks［J］. Journal of Artificial Societies and Social Simulation， 2008， 11（4）： 2.
[7]	Hussain A， Tahir A， Hussain Z， et al. Artificial intelligence-enabled analysis of public attitudes on Facebook and Twitter toward COVID-19 vaccines in the United Kingdom and the United States： Observational study［J］. Journal of Medical Internet Research， 2021， 23（4）： e26627.
[8]	Aral S， Walker D. Identifying influential and susceptible members of social networks［J］. Science， 2012， 337（6092）： 337-341.
[9]	Gruhl D， Guha R， Liben-Nowell D， et al. Information diffusion through blogspace［C］//Proceedings of the 13th International Conference on World Wide Web， New York NY USA，ACM， 2004： 491-501.
[10]	陈波，于泠，刘君亭，等. 泛在媒体环境下的网络舆情传播控制模型［J］. 系统工程理论与实践， 2011， 31（11）： 2140-2150.
	Chen B， Yu L， Liu J T， et al. Dissemination and control model of Internet public opinion in the ubiquitous media environments［J］. Systems Engineering—Theory & Practice， 2011， 31（11）： 2140-2150.
[11]	种大双，孙绍荣. 基于传染病模型的重大突发事件舆情传播与控制［J］. 情报理论与实践， 2018， 41（5）： 104-109.
	Chong D S， Sun S R. Public opinion dissemination and control of serious emergencies： Based on epidemic model［J］. Information Studies （Theory & Application）， 2018， 41（5）： 104-109.
[12]	Leskovec J， McGlohon M， Faloutsos C， et al. Patterns of cascading behavior in large blog graphs［C］//Proceedings of the 2007 SIAM International Conference on Data Mining，Society for Industrial and Applied Mathematics， Minneapolis， MN， USA，April 26-28，2007： 551-556.
[13]	李青，朱恒民. 基于BA网络的互联网舆情观点演化模型研究［J］. 情报杂志， 2012， 31（3）： 6-9+35.
	Li Q， Zhu H M. Study on the evolution model of the online public opinion viewpoint based on BA network［J］. Journal of Intelligence， 2012， 31（3）： 6-9+35.
[14]	魏静，黄阳江豪，林萍，等. 基于改进SIR模型的微博网络舆情传播研究［J］.情报科学，2019， 37（6）： 16-22.
	Wei J， Huang Y J H， Lin P， et al. Public opinion transmission of micro-blog network based on improved SIR model［J］. Information Science， 2019， 37（6）： 16-22.
[15]	魏静，丁乐蓉，朱恒民，等. 基于情感和亲密度的社交网络舆情传播模型研究［J］. 情报科学， 2021， 39（4）： 37-46.
	Wei J， Ding L R， Zhu H M， et al. Research on public opinion transmission model of social network based on emotion and intimacy［J］. Information Science， 2021， 39（4）： 37-46.
[16]	迟钰雪，刘怡君. 逆反心理的网络舆情传播机制研究［J］. 系统工程学报， 2019， 34（5）： 610-620.
	Chi Y X， Liu Y J. Study on the transmission mechanism of online public opinion of reverse psychology［J］. Journal of Systems Engineering，2019，34（5）： 610-620.
[17]	王明珠，郭林江，刘怡君. 考虑网民心理因素的网络舆情干预时机研究［J］. 中国管理科学， 2025， 33（6）： 140-150.
	Wang M Z， Guo L J， Liu Y J. Research on the timing of online public opinion intervention considering the psychological factors of netizens［J］. Chinese Journal of Management Science， 2025， 33（6）： 140-150.
[18]	朱光，颜燚，杨沁蓉. 基于SEIR演化博弈模型的网络维权策略及衍生舆情传播研究［J］. 情报科学， 2023， 41（3）： 89-99.
	Zhu G， Yan Y， Yang Q R. Network rights-protection strategy and derivative public opinion dissemination based on SEIR evolutionary game model［J］. Information Science， 2023， 41（3）： 89-99.
[19]	Du J， Kerkhof P， van Koningsbruggen G M. Predictors of social media self-control failure： Immediate gratifications， habitual checking， ubiquity， and notifications［J］. Cyberpsychology， Behavior， and Social Networking， 2019， 22（7）： 477-485.
[20]	Casey B J， Somerville L H， Gotlib I H， et al. Behavioral and neural correlates of delay of gratification 40 years later［J］. Proceedings of the National Academy of Sciences of the United States of America， 2011， 108（36）： 14998-15003.
[21]	Muraven M， Tice D M， Baumeister R F. Self-control as a limited resource： Regulatory depletion patterns［J］. Journal of Personality and Social Psychology， 1998， 74（3）： 774-789.
[22]	王梓宁，张国防. 考虑多交互关系与情感倾向的微博用户可信度评估算法［J］. 计算机应用研究， 2024， 41（10）： 3000-3007.
	Wang Z N， Zhang G F. Microblog users' credibility evaluation algorithm considering multi-interaction relationships and emotional tendencies［J］. Application Research of Computers， 2024， 41（10）： 3000-3007.
[23]	Ebbinghaus H. Memory： A contribution to experimental psychology［J］. Annals of Neurosciences， 2013， 20（4）： 200408.
[24]	中国政府网. 6月5日疫情防控最新消息！［EB/OL］. （2022-06-06）［2025-03-03］. .
	Chinese Government Website. Latest news on COVID-19 prevention and control as of June 5［EB/OL］.（2022-06-06）［2025-03-03］..
[25]	中国政府网. 国务院联防联控机制：各地要严格落实疫情防控“九不准”要求［EB/OL］. （2022-06-25）［2025-03-03］. .
	Chinese Government Website. Joint Prevention and Control Mechanism of the State Council： All localities must strictly implement the “Nine Prohibitions” requirements for epidemic prevention and control［EB/OL］. （2022-06-25）［2025-03-03］..
[26]	新华社. 严格执行第九版防控方案和“九不准”要求——国务院联防联控机制回答当前疫情防控有关问题［EB/OL］.（2022-07-22）［2025-03-03］..
	Xinhua News Agency. Strictly implement the ninth edition of the prevention and control plan and the “Nine Prohibitions” Requirements — Joint prevention and control mechanism of The State Council answers questions on current epidemic prevention and control［EB/OL］. （2022-07-22）［2025-03-03］..
[27]	卫生健康委网站. 国务院联防联控机制有关部门落实疫情防控“九不准”要求问题反映渠道［EB/OL］. （2022-07-10）［2025-03-03］. .
	National Health Commission Website. Feedback channels for issues concerning the implementation of the “Nine Prohibitions” Requirements for epidemic prevention and control by relevant departments of the joint prevention and control mechanism of the State Council［EB/OL］.（2022-07-10）［2025-03-03］..
[28]	央视网. 国家卫健委：对“九不准”现象开通公众留言板通报典型案例［EB/OL］. （2022-06-28）［2025-03-03］. .
	CCTV Website. National Health Commission： A public message board has been opened to report typical cases of “Nine Prohibitions” violations［EB/OL］.（2022-06-28）［2025-03-03］..
[29]	陈晨，袁绍军，尹兆磊，等. 一种分布式发电功率时间序列波动性量化评估方法［J］. 电子与信息学报， 2022， 44（11）： 3825-3832.
	Chen C， Yuan S J， Yin Z L， et al. A fluctuation quantitative evaluation method for distributed energy power time series［J］. Journal of Electronics & Information Technology， 2022， 44（11）： 3825-3832.
[30]	梁冉，徐雅斌. 基于改进SEIR模型的网络舆情传播研究［J］. 计算机仿真， 2023， 40（5）： 333-340.
	Liang R， Xu Y B. Research on network public opinion communication based on improved SERI model［J］. Computer Simulation， 2023， 40（5）： 333-340.

模型	参数取值
复杂网络	n=20000；m=8；Forget=0.663^[30]；p=0.2
IGSA-UFCS	α=0.2；β=0.5；γ=0.1；σ=0.1；θ=0.5；UN₀ =19500；FN₀ =0；CN₀ =500；SN₀ =0；B=0.01；C=1；D=0.2
IGSA-UFCS	用户初始即时满足心理强度的正态分布参数（u=0.5，σ=1）
IGSA-UFCS	用户自我调节能力的正态分布参数（u=0.5，σ=1）
IGSA-UFCS	用户最长自我调节天数的正态分布参数（u=70，σ=7）
IGSA-UFCS	用户仅即时满足心理生效天数的正态分布参数（u=14，σ=7）
IGSA-UFCS	用户粉丝数的幂律分布参数（λ=2.5）
遗传算法	交叉概率=0.2；变异概率=0.2；迭代次数=50；种群数量=90

效果	措施1	措施2	措施3	措施4
5%	(2830,3241,242.05)	(3290,3709,299.7)	(2220,2533,52)	(2703,3119,217.9)
10%	(2324,2669,176.3)	(2437,2697,59.25)	(1846,2115,43.1)	(1770,2073,40.85)
15%	(1814,2136,124.75)	(2413,2737,54.65)	(1483,1789,33.65)	(1417,1729,33.9)
20%	(1398,1633,97.25)	(2331,2562,50.45)	(1115,1387,18.15)	(1050,1333,20.95)
25%	(967,1125,63.9)	(2272,2624,51.5)	(783,994,12.15)	(637,903,10.75)

Research on the Evolution Mechanism of Weibo User Discussion Heat for Public Demand Response Policies——A Case Based on Weibo Users Data

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 17

References 30

Related Articles 15

Metrics

Comments

Recommended 0

[1]	Huali Sun, Chenxin Ma, Junge Zhang. Research on Response Strategy Considering Low-interest Loans and Business Interruption Insurance under the Supply Disruption Risk [J]. Chinese Journal of Management Science, 2026, 34(5): 342-350.
[2]	Ming Liu, Jie Wang, Jie Cao. Modeling and Optimization of Emergency Counterpart Assistance Relationship Based on Comprehensive Matching Degree [J]. Chinese Journal of Management Science, 2026, 34(10): 209-219.
[3]	Wenhui Qi, Hong Chi, Mingliang Qi, Shouhao Zhang. Simulation Study on Nuclear Emergency Evacuation Considering Residents' Dynamic Decision-making [J]. Chinese Journal of Management Science, 2025, 33(5): 259-267.
[4]	Fengjiao Chen,Dehai Liu. Evolutionary Path Analysis of Multi-channel Epidemic Information Release of Major Infectious Diseases [J]. Chinese Journal of Management Science, 2024, 32(4): 237-249.
[5]	Wenhui Qi, Mingliang Qi. Research on the Effect Path to Resident Cooperation Intention under Nuclear Emergency Evacuation Scenarios:A Case of Haiyang Nuclear Power Plant [J]. Chinese Journal of Management Science, 2024, 32(12): 225-234.
[6]	Mu DU. A Data-driven Decision-making Approach for Joint Mass Screening and Pharmaceutical Resource Allocation in Epidemic Outbreak [J]. Chinese Journal of Management Science, 2024, 32(11): 168-179.
[7]	Tianjiao Li, Dehai Liu. Research of Territorial Inner Principal on Material Dynamic Allocation for Sudden Public Health Events Based on Differential Games [J]. Chinese Journal of Management Science, 2024, 32(11): 233-242.
[8]	Wei-jian JIN,Hao XU,Chuan-feng HUANG,Cheng-zhi JIANG. Research on Emergency Management Decision of Large-scale Epidemic Based on Prospect Theory [J]. Chinese Journal of Management Science, 2023, 31(10): 225-233.
[9]	GAO Lei, GONG Jing. Analysis Model for Infrastructure Resilience Based on Linear Piecewise Recovery Function——A Case Study of C County Power Network [J]. Chinese Journal of Management Science, 2022, 30(12): 86-95.
[10]	LIU Yang, LIU Xiao-yun, LI Yu-fei. Evaluation of Campus Emergency Management Capability Based on Improved Matter-Element Extension Model [J]. Chinese Journal of Management Science, 2022, 30(11): 299-308.
[11]	ZHANG Ding-hua, LI Wei-jun, LI Cheng, SHEN Shi-fei. The Researchon the Analysis and Prediction of Mass Incidentsin Multi-dimensional Scenario Space Based on Deep Learning [J]. Chinese Journal of Management Science, 2020, 28(8): 172-180.
[12]	SONG Min-xue, LIU De-hai. Stochastic Evolutionary Game Model for Resolution Mechanism of Mass Events [J]. Chinese Journal of Management Science, 2020, 28(4): 142-152.
[13]	WANG Xi-hui, ZHANG Wen-xin, YU Yu-gang, LIU Bing-bing. An Optimization Model for Emergency Shelter Location and Relief Materials Allocation Considering Human Suffering [J]. Chinese Journal of Management Science, 2020, 28(12): 162-172.
[14]	ZHAO Rong, LIU Ke-yan, REN Pei-yu. Min-max Multiple Sink Location Problem in Dynamic Path Networks with Different Traffic Capacity Constraint [J]. Chinese Journal of Management Science, 2017, 25(9): 133-140.
[15]	DENG Jie, CHI Hong, XU Bao-guang. The Research on Emergency Response Procedures Modularity Based on the Similarity of Directed Graph [J]. Chinese Journal of Management Science, 2017, 25(4): 115-123.