Please wait a minute...
Data Analysis and Knowledge Discovery  2022, Vol. 6 Issue (7): 128-140    DOI: 10.11925/infotech.2096-3467.2021.0711
Original article Current Issue | Archive | Adv Search |
Evolution of Public Sentiments During COVID-19 Pandemic
Bian Xiaohui1(),Xu Tong2
1School of Management, Anhui University, Hefei 230039, China
2School of Computer Science, University of Science and Technology of China, Hefei 230027, China
Download: PDF (4275 KB)   HTML ( 37
Export: BibTeX | EndNote (RIS)      
Abstract  

[Objective] This study analyzes the social media posts during the COVID-19 pandemic, aiming to reveal the temporal and spatial differences of public opinion, the sentiment evolution under different circumstances, as well as the trans-regional spreading of the public sentiments. [Methods] Firstly, we utilized the Latent Dirichlet Allocation (LDA) model to generate the latent topics and related keyword groups, which also analyzed public sentiment evolutions from the perspectives of global and individual topics. Then, we described the trans-regional spread of public sentiments based on the social spread model adapted from the classic Independent Cascade Model. [Results] The new model summarized the general rules of the temporal evolution and spatial difference, as well as the impacts of distance to the epidemic centers and the financial levels. We also found two different types of topics indicating reasons for popularity and sentiment differences, as well as multi-view connections among these topics. The strength of trans-regional sentiment spread could be affected by both regional distance and epidemic situation. [Limitations] The new framework could not process the multimodal data. [Conclusions] The proposed model helps the local government make better strategies according to specific conditions, and pay more attention to the impacts of related events. They should also strengthen regional cooperation and coordination for controlling pandemics and monitoring public sentiments.

Key wordsPublic Health Emergency      Weibo Public Sentiment      Sentiment Evolution      Topic Analysis      Spatio-Temporal Analysis     
Received: 16 July 2021      Published: 24 August 2022
ZTFLH:  G203  
Fund:National Social Science Fund of China(16CZZ025)
Corresponding Authors: Bian Xiaohui,ORCID:0000-0002-1583-971X     E-mail: bianxh@ahu.edu.cn

Cite this article:

Bian Xiaohui, Xu Tong. Evolution of Public Sentiments During COVID-19 Pandemic. Data Analysis and Knowledge Discovery, 2022, 6(7): 128-140.

URL:

https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/10.11925/infotech.2096-3467.2021.0711     OR     https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/Y2022/V6/I7/128

关键词类别 关键词列表
直接相关 武汉、疫情、肺炎、新冠、冠状病毒、口罩
事件相关 野味、海鲜市场、红十字会、复工、医疗队、卫健委
人名相关 钟南山、李文亮、李兰娟、高福
诊断相关 确诊、疑似、发热、体温
Keywords for Judging the Relevance of the Epidemic-Related Microblogs
情感大类 情感子类 微博数量 微博比重
快乐、安心 16 665 5.86%
尊敬、赞扬、相信、喜爱、祝愿 190 212 66.87%
愤怒 1 637 0.58%
悲伤、失望、内疚、思念 9 741 3.42%
慌、恐惧、羞 23 177 8.15%
烦闷、憎恶、贬责、妒忌、怀疑 41 708 14.66%
惊奇 1 309 0.46%
Sentiment Distribution of the Epidemic-Related Microblogs
Temporal Change in the Proportion of Positive Emotion Microblogs
Temporal Change in the Number of Negative Emotion Microblogs
分层类别 分层依据 包含省份
核心层 湖北本省(1个) 湖北
邻近层 湖北邻省(6个) 安徽、重庆、陕西、江西、湖南、河南
间隔层 湖北邻省的邻近省份(13个) 山东、浙江、江苏、甘肃、贵州、四川、山西、宁夏、内蒙古、福建、广东、广西、河北
边缘层 其他省份(11个) 黑龙江、吉林、辽宁、海南、上海、北京、天津、新疆、青海、云南、西藏
Province Stratification Based on Geographic Distance Level
Proportion Change of the 6 Emotions at Different Geographic Distance Level
经济水平分层 人均GDP区间(元) 包含省份
发达省份(10个) 164 197~70 733 北京、上海、江苏、浙江、福建、广东、天津、湖北、重庆、山东
中等省份(11个) 67 926~53 269 内蒙古、陕西、安徽、湖南、海南、辽宁、河南、四川、新疆、宁夏、江西
落后省份(10个) 49 381~33 058 西藏、青海、云南、贵州、河北、山西、吉林、广西、黑龙江、甘肃
Province Stratification Based on Economic Development Level
Proportion Change of the 6 Emotions at Different Economic Development Level
主题类别 主题编号 微博
数量
主题
相关性
政府公告与疫情通报 6、10、12、38、40、48 87 433 0.148 3
疫情日常交流 1、4、9、29、31、33、34、
47、50
36 383 0.171 3
热点事件讨论 2、11、15、35、39、43、49 4 547 0.164 3
疫情求助 7、17 3 743 0.120 8
物资捐赠与公益活动 5、8、26、36、41 2 053 0.111 9
医护人员、专家组报道 3、14、32、44、46 1 834 0.131 8
治疗方案及科研进展
政府行政管理报道
13、20、23
19、21、22、24、27、30、37
1 109
731
0.134 6
0.145 8
海外疫情 16、28、42 313 0.128 1
视频配属文字 25 46 074 0.128 6
Microblog Proportion of Different Event Topics
Keywords Related to Official Announcement and Seeking Help
Keywords Related to Hot Events
Emotion Tendency for Topic 10 (Government Announcement)
Emotion Tendency for Topic 38 and Topic 50
Emotion Tendency for Topic 35 and Topic 39
[1] An L, Yu C M, Lin X, et al. Topical Evolution Patterns and Temporal Trends of Microblogs on Public Health Emergencies[J]. Online Information Review, 2018, 42(6): 821-846.
doi: 10.1108/OIR-04-2016-0100
[2] Palen L, Anderson K M. Crisis Informatics—New Data for Extraordinary Times[J]. Science, 2016, 353(6296): 224-225.
doi: 10.1126/science.aag2579
[3] 卢嘉, 刘新传, 李伯亮. 社交媒体公共讨论中理智与情感的传播机制——基于新浪微博的实证研究[J]. 现代传播(中国传媒大学学报), 2017, 39(2): 73-79.
[3] Lu Jia, Liu Xinchuan, Li Boliang. The Spreading Mechanism of Reason and Emotion in Public Discussions on Social Media—An Empirical Study Based on Sina Weibo[J]. Modern Communication(Journal of Communication University of China), 2017, 39(2): 73-79.)
[4] Reuter C, Spielhofer T. Towards Social Resilience: A Quantitative and Qualitative Survey on Citizens’ Perception of Social Media in Emergencies in Europe[J]. Technological Forecasting and Social Change, 2017, 121: 168-180.
doi: 10.1016/j.techfore.2016.07.038
[5] 陈业华, 张晓倩. 网络突发群体事件网民群体情绪传播模型及仿真研究[J]. 情报科学, 2018, 36(3): 151-156.
[5] ( Chen Yehua, Zhang Xiaoqian. Research on Netizen Group Emotion Contagion Model and the Simulation Under Network Group Emergencies[J]. Information Science, 2018, 36(3): 151-156.)
[6] 杨阳, 王杰. 情绪因素影响下的突发事件网络舆情演化研究[J]. 情报科学, 2020, 38(3): 35-41.
[6] ( Yang Yang, Wang Jie. The Evolution of Emergency Network Public Opinion Influenced by Emotional Factors[J]. Information Science, 2020, 38(3): 35-41.)
[7] 鲁艳霞, 吴迪, 黄川林. 大数据环境下面向突发公共事件的微博用户情绪分析[J]. 软件工程, 2017, 20(1): 45-48.
[7] ( Lu Yanxia, Wu Di, Huang Chuanlin. An Analysis of Micro-Blog Users’ Emotions in Public Emergencies Based on Big Data[J]. Software Engineering, 2017, 20(1): 45-48.)
[8] 张雪, 陈安. 基于网络新闻评论的群体愤怒情绪监测与度量[J]. 科技促进发展, 2010(9): 44-49.
[8] ( Zhang Xue, Chen An. The Monitoring and Measurement of Mood of Anger Based on Network Review of News[J]. Science & Technology for Development, 2010(9): 44-49.)
[9] Fan R, Zhao J C, Chen Y, et al. Anger is More Influential than Joy: Sentiment Correlation in Weibo[J]. PLoS One, 2014, 9(10): e110184.
[10] 李聪. 问题疫苗事件微博传播中的情绪与表达[D]. 武汉: 武汉大学, 2019.
[10] ( Li Cong. Emotions and Expressions in Weibo Communication of Vaccine Events[D]. Wuhan: Wuhan University, 2019.)
[11] 陈曦, 费奇, 李炜. 基于计算实验的公众恐慌研究初探[J]. 华中科技大学学报(社会科学版), 2009, 23(2): 34-37.
[11] Chen Xi, Fei Qi, Li Wei. A Preliminary Research on Urban Mass Panic Based on Computational Methods for Experiment[J]. Journal of Huazhong University of Science and Technology(Social Science Edition), 2009, 23(2): 34-37.)
[12] 王春雪, 吕淑然, 杨凯. 突发事件中恐惧情绪感染概率研究[J]. 中国安全科学学报, 2015, 25(9): 14-19.
[12] ( Wang Chunxue, Lyu Shuran, Yang Kai. Research on Probability of Fear Contagion in Emergency[J]. China Safety Science Journal, 2015, 25(9): 14-19.)
[13] 安璐, 吴林. 融合主题与情感特征的突发事件微博舆情演化分析[J]. 图书情报工作, 2017, 61(15): 120-129.
doi: 10.13266/j.issn.0252-3116.2017.15.014
[13] ( An Lu, Wu Lin. An Integrated Analysis of Topical and Emotional Evolution of Microblog Public Opinions on Public Emergencies[J]. Library and Information Service, 2017, 61(15): 120-129.)
doi: 10.13266/j.issn.0252-3116.2017.15.014
[14] 叶勇豪, 许燕, 朱一杰, 等. 网民对“人祸”事件的道德情绪特点——基于微博大数据研究[J]. 心理学报, 2016, 48(3): 290-304.
doi: 10.3724/SP.J.1041.2016.00290
[14] ( Ye Yonghao, Xu Yan, Zhu Yijie, et al. The Characteristics of Moral Emotions of Chinese Netizens Towards an Anthropogenic Hazard: A Sentiment Analysis on Weibo[J]. Acta Psychologica Sinica, 2016, 48(3): 290-304.)
doi: 10.3724/SP.J.1041.2016.00290
[15] Trope Y, Liberman N. Construal-Level Theory of Psychological Distance[J]. Psychological Review, 2010, 117(2): 440-463.
doi: 10.1037/a0018963
[16] 钱铭怡, 叶冬梅, 董葳, 等. 不同时期北京人对SARS的应对行为、认知评价和情绪状态的变化[J]. 中国心理卫生杂志, 2003, 17(8): 515-520.
[16] ( Qian Mingyi, Ye Dongmei, Dong Wei, et al. Behaviour, Cognition and Emotion of the Public in Beijing Towards SARS[J]. Chinese Mental Health Journal, 2003, 17(8): 515-520.)
[17] van Lent L G, Sungur H, Kunneman F A, et al. Measuring Public Attention and Fear for Ebola Using Twitter[J]. Journal of Medical Internet Research, 2017, 19(6): e193.
doi: 10.2196/jmir.7219
[18] 张放, 甘浩辰. 疫情心理时空距离对公众情绪的影响研究——基于新冠肺炎疫期微博文本面板数据的计算分析[J]. 新闻界, 2020(6): 39-49.
[18] ( Zhang Fang, Gan Haochen. On the Influence of Temporal and Spatial Distance from Epidemic on Public Sentiment: A Computational Analysis Based on Panel Data of Weibo Text About COVID-19[J]. Journalism and Mass Communication Monthly, 2020(6): 39-49.)
[19] 唐超. 网络情绪演进的实证研究[J]. 情报杂志, 2012, 31(10): 48-52.
[19] ( Tang Chao. Empirical Research on the Evolution of Online Emotion[J]. Journal of Intelligence, 2012, 31(10): 48-52.)
[20] 单斌, 李芳. 基于LDA话题演化研究方法综述[J]. 中文信息学报, 2010, 24(6): 43-49.
[20] ( Shan Bin, Li Fang. A Survey of Topic Evolution Based on LDA[J]. Journal of Chinese Information Processing, 2010, 24(6): 43-49.)
[21] 赵晓航. 基于情感分析与主题分析的“后微博”时代突发事件政府信息公开研究——以新浪微博“天津爆炸”话题为例[J]. 图书情报工作, 2016, 60(20): 104-111.
doi: 10.13266/j.issn.0252-3116.2016.20.013
[21] ( Zhao Xiaohang. The Study on Government News Release in the Era of Post-Microblog Based on Sentiment Analysis and Subject Analysis: A Case Study of the “Tianjin Explosion” on Sina Microblog[J]. Library and Information Service, 2016, 60(20): 104-111.)
doi: 10.13266/j.issn.0252-3116.2016.20.013
[22] 任中杰, 张鹏, 李思成, 等. 基于微博数据挖掘的突发事件情感态势演化分析——以天津8·12事故为例[J]. 情报杂志, 2019, 38(2): 140-148.
[22] ( Ren Zhongjie, Zhang Peng, Li Sicheng, et al. Analysis of Emotion Evolution of Emergencies Based on Weibo Data Mining: Taking “8·12 Accident in Tianjin” as an Example[J]. Journal of Intelligence, 2019, 38(2): 140-148.)
[23] 陈建美. 中文情感词汇本体的构建及其应用[D]. 大连: 大连理工大学, 2009.
[23] ( Chen Jianmei. The Construction and Application of Chinese Emotion Word Ontology[D]. Dalian: Dalian University of Technology, 2009.)
[24] 刘云中, 林亚平, 陈治平. 基于隐马尔可夫模型的文本信息抽取[J]. 系统仿真学报, 2004, 16(3): 507-510.
[24] ( Liu Yunzhong, Lin Yaping, Chen Zhiping. Text Information Extraction Based on Hidden Markov Model[J]. Acta Simulata Systematica Sinica, 2004, 16(3): 507-510.)
[25] Blei D M, Ng A Y, Jordan M I. Latent Dirichlet Allocation[J]. Journal of Machine Learning Research, 2003, 3: 993-1022.
[26] 李纲, 陈思菁, 毛进, 等. 自然灾害事件微博热点话题的时空对比分析[J]. 数据分析与知识发现, 2019, 3(11): 1-15.
[26] ( Li Gang, Chen Sijing, Mao Jin, et al. Spatio-Temporal Comparison of Microblog Trending Topics on Natural Disasters[J]. Data Analysis and Knowledge Discovery, 2019, 3(11): 1-15.)
[27] Xu T, Zhu H S, Zhao X Y, et al. Taxi Driving Behavior Analysis in Latent Vehicle-to-Vehicle Networks: A Social Influence Perspective[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016: 1285-1294.
[28] Kempe D, Kleinberg J, Tardos É. Maximizing the Spread of Influence Through a Social Network[C]// Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2003: 137-146.
[1] Yi Huifang,Liu Xiwen. Analyzing Patent Technology Topics with IPC Context-Enhanced Context-LDA Model[J]. 数据分析与知识发现, 2021, 5(4): 25-36.
[2] Zhang Yipeng,Ma Jingdong. Analyzing Sentiments and Dissemination of Misinformation on Public Health Emergency[J]. 数据分析与知识发现, 2020, 4(12): 45-54.
[3] Lu An,Yanping Liang. Selection of Users’ Behaviors Towards Different Topics of Microblog on Public Health Emergencies[J]. 数据分析与知识发现, 2019, 3(4): 33-41.
[4] Gang Li,Sijing Chen,Jin Mao,Yansong Gu. Spatio-Temporal Comparison of Microblog Trending Topics on Natural Disasters[J]. 数据分析与知识发现, 2019, 3(11): 1-15.
[5] Yu Yan,Zhao Naixuan. Choosing Stopwords for Patent Topic Analysis Based on Auxiliary Set[J]. 数据分析与知识发现, 2018, 2(11): 95-103.
  Copyright © 2016 Data Analysis and Knowledge Discovery   Tel/Fax:(010)82626611-6626,82624938   E-mail:jishu@mail.las.ac.cn