Please wait a minute...
Data Analysis and Knowledge Discovery  2021, Vol. 5 Issue (6): 66-79    DOI: 10.11925/infotech.2096-3467.2020.1258
Current Issue | Archive | Adv Search |
Patterns and Evolution of Public Opinion on Weibo During Natural Disasters: Case Study of Typhoons and Rainstorms
Ma Yingxue,Zhao Jichang()
School of Economics and Management, Beihang University, Beijing 100191, China
Download: PDF (1673 KB)   HTML ( 27
Export: BibTeX | EndNote (RIS)      

[Objective] This study reveals patterns and evolution of public opinion on Weibo during natural disasters from the perspectives of trending topics and information dissemination. [Methods] We proposed a machine learning approach to extract the valid data of natural disasters from Weibo. Then, we employed a deep learning model to cluster these textual posts. Finally, we investigated the information dissemination patterns with complex network analysis. [Results] The accuracy of our extractor for valid disaster information reached 0.82. The clusters of textual posts indicated the changes of trending topics. The structure of information dissemination during disasters was sparse. The sizes of online communities expanded constantly while their distribution unchanged. Users in different regions had different preferences for information sources. [Limitations] We did not conduct experiment to examine data from different social platforms. [Conclusions] The proposed method could effectively identify public opinion events during natural disasters.

Key wordsSocial Media      Topic Mining      Social Network      Public Opinion Management      Information Dissemination     
Received: 15 December 2020      Published: 06 July 2021
ZTFLH:  TP391  
Fund:National Natural Science Foundation of China(71871006)
Corresponding Authors: Zhao Jichang     E-mail:

Cite this article:

Ma Yingxue,Zhao Jichang. Patterns and Evolution of Public Opinion on Weibo During Natural Disasters: Case Study of Typhoons and Rainstorms. Data Analysis and Knowledge Discovery, 2021, 5(6): 66-79.

URL:     OR

Research Framework of Public Response Analysis During Disasters on Weibo
标签 查准率 查全率 F1值 样本量
0 0.81 0.64 0.71 201
1 0.83 0.92 0.88 399
Algorithm Performance on Typhoon Data Set
标签 查准率 查全率 F1值 样本量
0 0.75 0.67 0.71 188
1 0.86 0.90 0.88 412
Algorithm Performance on Rainstorm Data Set
Comparison of Data Volume Before and After Filtering
The Proportion of Forwarded Tweets
Algorithm Diagram of DEC Model
聚类标签 数量 占比/%
cluster_0 29 248 39.93
cluster_1 7 276 9.93
cluster_2 7 765 10.60
cluster_3 9 069 12.38
cluster_4 11 053 15.09
cluster_5 8 831 12.06
总量 73 242 100.00
Data Clustering Results Before Landing
聚类标签 数量 占比/%
cluster_0 6 542 12.87
cluster_1 7 415 14.59
cluster_2 7 050 13.87
cluster_3 17 342 34.12
cluster_4 5 665 11.15
cluster_5 6 808 13.40
总量 50 822 100.00
Data Clustering Results After Landing
聚类标签 前 20 关键词 文本描述
cluster_0 台风,吹到,装好,来场,丢人,那多,说走就走,行李,别人,旅行,信用卡,要来,万一,带上,期待,害怕,怎么办,听说,阳台,偷笑 轻松语境,偏生活、玩耍类
cluster_1 台风,登陆,台湾,尼伯特,强台风,新闻,原子弹,最强,网易,我国,沿海,台东,轰炸,福建,今年,阵风,华东,初台,分享,太麻里 台风登陆台湾、台风威力报道
cluster_2 台风,尼伯特,停运,影响,福建,列车,铁路,车票,旅客列车,部分,厦门,停售,福州,旅客,今年,沿海,强台风,航班,登陆,温福 台风造成的交通影响
cluster_3 台风,天空,尼伯特,天气,前夕,来临,吃惊,要来,微风,福州,这么,一个,今天,这个,厦门,可以,浮云,之前,真是,啤酒 多为无较大意义类短文本
cluster_4 台风,尼伯特,暴雨,预警,中心,华东,橙色,靠近,今年,安徽,湖北,发布,公里,台湾,今天,热带风暴,沿海,登陆,中央气象台,位于 台风播报和气象预警
cluster_5 台风,尼伯特,工作,响应,应急,防御,防汛,启动,防汛防台,做好,影响,今年,国家, 部署,强台风,防总,长江,可能,暴雨,准备 部署措施、应急防范类
Keywords and Descriptions of Different Clusters Before Landing
聚类标签 前 20 关键词 文本描述
cluster_0 台风,尼伯特,厦门,限贷,政策,第一号,楼市,国土资源,过后,过境,微笑,房产,看不出,来临,出去,管理局,感觉,明天,生变,厦门 生活类短文本
cluster_1 台风,尼伯特,影响,减弱,热带,低压,今天,今年,中心,暴雨,预计,福建,登陆,天气, 防汛,局部,宁化县,境内,气象台,福建省 台风播报及气象预报
cluster_2 台风,倒计时,登陆,景泰,拜拜,酸酸的,上海,草根,直通车,讲信用,哈哈,老头,警民,虎头蛇尾,江中,泥石流,卷入,市民,假期,谢谢 一些社会事件
cluster_3 台风,装好,吹到,说好,说走就走,丢人,万一,那多,行李,听说,旅行,有多严,要来,来场,带上,拜拜,信用卡,别人,害怕,期待 调侃类、口语化表达
cluster_4 台风,尼伯特,死亡,福建,失踪,万人,民政部,已致,受灾,福建省,台湾,紧急,新闻,造成,网易,台东,国家,转移, 因灾,今年 台风影响及灾害损失
cluster_5 台风,尼伯特,闽清,福建,福州,闽清县,影响,永泰,消防,洪水,救援,部分,灾区,今年,坂东镇,冲塌,坂东,严重,防抗,乡镇 受损及救灾情况
Keywords and Descriptions of Different Clusters After Landing
Posting Time of Different Clusters of Tweets
Emotions in Different Clusters of Tweets
聚类标签 转发占比 前 3 转发来源
cluster_0 0.10 @姚晨、@江宁公安在线、@北京厨子新号
cluster_1 0.11 @中国气象爱好者、@温州草根新闻、@中国天气
cluster_2 0.19 @南昌铁路、@新浪厦门、@南京发布
cluster_3 0.06 @青春影视偶像、@张鹤慈、@福州身边事儿
cluster_4 0.32 @央视新闻、@人民日报、@中央气象台
cluster_5 0.17 @头条新闻、@中国消防、@新浪上海
Forwarding Sources of Different Clusters Before Landing
聚类标签 转发占比 前 3 转发来源
cluster_0 0.06 @中央气象台、@中国气象爱好者、@中国铁路
cluster_1 0.12 @中国气象爱好者、@来去之间、@中央气象台
cluster_2 0.28 @警民直通车-上海、@人民日报、@福州日报
cluster_3 0.06 @美食上海站、@杭州微博城事、@天涯明月刀OL官微
cluster_4 0.16 @南昌铁路、@中国新闻网、@全球头条新闻事件
cluster_5 0.19 @新浪福建、@安徽消防、@福建身边事
Forwarding Sources of Different Clusters After Landing
台风名 总微博量 包含转发微博量 含转发的微博占比 总节点数 总边数 所有边权重和
尼伯特 165 871 26 212 15.80% 25 288 24 053 25 899
妮妲 108 956 9 497 8.72% 9 690 8 615 9 276
莫兰蒂 122 975 19 672 16.00% 17 112 16 232 19 273
鲇鱼 94 249 8 132 8.63% 7 927 7 090 7 935
海马 1141 46 9 570 8.38% 8 682 7 550 9 341
Features of Forwarding Networks
Sizes of Forwarding Networks Over Time
Size Distribution of Connected Components of Forwarding Networks Over Time
A Sample Randomly Extracted from a Forwarding Network
[1] Alexander D E. Social Media in Disaster Risk Reduction and Crisis Management[J]. Science and Engineering Ethics, 2014,20(3):717-733.
doi: 10.1007/s11948-013-9502-z pmid: 24306994
[2] Yin J, Karimi S, Lampert A, et al. Using Social Media to Enhance Emergency Situation Awareness[C]// Proceedings of the 24th International Joint Conference on Artificial Intelligence. 2015.
[3] Imran M, Castillo C. Towards a Data-Driven Approach to Identify Crisis-Related Topics in Social Media Streams[C]// Proceedings of the 24th International Conference on World Wide Web. 2015: 1205-1210.
[4] Kejriwal M, Zhou P L. Low-Supervision Urgency Detection and Transfer in Short Crisis Messages[C]// Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining. 2019: 353-356.
[5] Chae J, Thom D, Jang Y, et al. Public Behavior Response Analysis in Disaster Events Utilizing Visual Analytics of Microblog Data[J]. Computers & Graphics, 2014,38:51-60.
doi: 10.1016/j.cag.2013.10.008
[6] Cresci S, Cimino A, Dell’Orletta F, et al. Crisis Mapping During Natural Disasters via Text Analysis of Social Media Messages[C]// Proceedings of 2015 International Conference on Web Information Systems Engineering. 2015: 250-258.
[7] Kryvasheyeu Y, Chen H H, Obradovich N, et al. Rapid Assessment of Disaster Damage Using Social Media Activity[J]. Science Advances, 2016,2(3):e1500779.
doi: 10.1126/sciadv.1500779
[8] Nguyen D T, Ofli F, Imran M, et al. Damage Assessment from Social Media Imagery Data During Disasters[C]// Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining. 2017.
[9] Madichetty S, Muthukumarasamy S. Disaster Damage Assessment from the Tweets Using the Combination of Statistical Features and Informative Words[J]. Social Network Analysis and Mining, 2019,9(1):42.
doi: 10.1007/s13278-019-0579-5
[10] Resch B, Usländer F, Havas C. Combining Machine-Learning Topic Models and Spatiotemporal Analysis of Social Media Data for Disaster Footprint and Damage Assessment[J]. Cartography and Geographic Information Science, 2018,45(4):362-376.
doi: 10.1080/15230406.2017.1356242
[11] Fast S M, González M C, Wilson J M, et al. Modelling the Propagation of Social Response During a Disease Outbreak[J]. Journal of the Royal Society Interface, 2015,12(104):20141105.
doi: 10.1098/rsif.2014.1105
[12] Yang D, Chow T W, Zhong L, et al. True and Fake Information Spreading over the Facebook[J]. Physica A: Statistical Mechanics and Its Applications, 2018,505:984-994.
doi: 10.1016/j.physa.2018.04.026
[13] Zeng L, Starbird K, Spiro E S. Rumors at the Speed of Light? Modeling the Rate of Rumor Transmission During Crisis[C]// Proceedings of the 49th Hawaii International Conference on System Sciences (HICSS). 2016: 1969-1978.
[14] Yuan R F, Zhou Q F, Zhou W B. dTexSL: A Dynamic Disaster Textual Storyline Generating Framework[J]. World Wide Web, 2019,22(5):1913-1933.
doi: 10.1007/s11280-018-0640-8
[15] Shan S Q, Zhao F, Wei Y G, et al. Disaster Management 2.0: A Real-Time Disaster Damage Assessment Model Based on Mobile Social Media Data—A Case Study of Weibo (Chinese Twitter)[J]. Safety Science, 2019,115:393-413.
doi: 10.1016/j.ssci.2019.02.029
[16] Imran M, Elbassuoni S, Castillo C, et al. Practical Extraction of Disaster-Relevant Information from Social Media[C]// Proceedings of the 22nd International Conference on World Wide Web. 2013: 1021-1024.
[17] Imran M, Elbassuoni S, Castillo C, et al. Extracting Information Nuggets from Disaster-Related Messages in Social Media[C]// Proceedings of the 10th International ISCRAM Conference. 2013.
[18] Nguyen D T, Joty S, Imran M, et al. Applications of Online Deep Learning for Crisis Response Using Social Media Information[OL]. arXiv Preprint, arXiv:1610.01030.
[19] Interdonato R, Guillaume J L, Doucet A. A Lightweight and Multilingual Framework for Crisis Information Extraction from Twitter Data[J]. Social Network Analysis and Mining, 2019,9(1):65.
doi: 10.1007/s13278-019-0608-4
[20] Kim J, Hastak M. Social Network Analysis: Characteristics of Online Social Networks after a Disaster[J]. International Journal of Information Management, 2018,38(1):86-96.
doi: 10.1016/j.ijinfomgt.2017.08.003
[21] Niles M T, Emery B F, Reagan A J, et al. Social Media Usage Patterns During Natural Hazards[J]. PLoS One, 2019,14(2):e0210484.
doi: 10.1371/journal.pone.0210484
[22] Kryvasheyeu Y, Chen H H, Moro E, et al. Performance of Social Network Sensors During Hurricane Sandy[J]. PLoS one, 2015,10(2):e0117288.
doi: 10.1371/journal.pone.0117288
[23] Li L F, Zhang Q P, Tian J, et al. Characterizing Information Propagation Patterns in Emergencies: A Case Study with Yiliang Earthquake[J]. International Journal of Information Management, 2018,38(1):34-41.
doi: 10.1016/j.ijinfomgt.2017.08.008
[24] Shi B W, Zhao J C, Xu K. A Word2Vec Model for Sentiment Analysis of Weibo[C]// Proceedings of the 16th International Conference on Service Systems and Service Management (ICSSSM). IEEE, 2019: 1-6.
[25] Xie J Y, Girshick R, Farhadi A. Unsupervised Deep Embedding for Clustering Analysis[C]// Proceedings of the 33rd International Conference on Machine Learning. 2016: 478-487.
[26] Borge-Holthoefer J, Rivero A, García I, et al. Structural and Dynamical Patterns on Online Social Networks: The Spanish May 15th Movement as a Case Study[J]. PLoS One, 2011,6(8):e23883.
doi: 10.1371/journal.pone.0023883
[1] Xie Hao,Mao Jin,Li Gang. Sentiment Classification of Image-Text Information with Multi-Layer Semantic Fusion[J]. 数据分析与知识发现, 2021, 5(6): 103-114.
[2] Wang Xiwei,Jia Ruonan,Wei Yanan,Zhang Liu. Clustering User Groups of Public Opinion Events from Multi-dimensional Social Network[J]. 数据分析与知识发现, 2021, 5(6): 25-35.
[3] Gao Yilin,Min Chao. Comparing Technology Diffusion Structure of China and the U.S. to Countries Along the Belt and Road[J]. 数据分析与知识发现, 2021, 5(6): 80-92.
[4] Zhang Guobiao,Li Jie. Detecting Social Media Fake News with Semantic Consistency Between Multi-model Contents[J]. 数据分析与知识发现, 2021, 5(5): 21-29.
[5] Li Yueyan,Wang Hao,Deng Sanhong,Wang Wei. Research Trends of Information Retrieval——Case Study of SIGIR Conference Papers[J]. 数据分析与知识发现, 2021, 5(4): 13-24.
[6] Xu Yabin, Sun Qiutian. Identifying Leaders and Dissemination Paths of Public Opinion[J]. 数据分析与知识发现, 2021, 5(2): 32-42.
[7] Liu Qian, Li Chenliang. A Survey of Topic Evolution on Social Media[J]. 数据分析与知识发现, 2020, 4(8): 1-14.
[8] Li Gang, Guan Weidong, Ma Yaxue, Mao Jin. Predicting Social Media Visibility of Scholarly Articles[J]. 数据分析与知识发现, 2020, 4(8): 63-74.
[9] 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.
[10] Ying Tan,Jin Zhang,Lixin Xia. A Survey of Sentiment Analysis on Social Media[J]. 数据分析与知识发现, 2020, 4(1): 1-11.
[11] Peng Guan,Yuefen Wang. Advances in Patent Network[J]. 数据分析与知识发现, 2020, 4(1): 26-39.
[12] Manyu Huang,Qi Yun,Hufeng Peng,Xuemeng Dou. Analyzing Textual Features of Excess-funded Agricultural Products——Case Study of Crowdfunding Website[J]. 数据分析与知识发现, 2019, 3(9): 124-134.
[13] Yan Wen,Lijian Ma,Qingtian Zeng,Wenyan Guo. POI Recommendation Based on Geographic and Social Relationship Preferences[J]. 数据分析与知识发现, 2019, 3(8): 30-39.
[14] Liqing Qiu,Wei Jia,Xin Fan. Influence Maximization Algorithm Based on Overlapping Community[J]. 数据分析与知识发现, 2019, 3(7): 94-102.
[15] Xiaolan Wu,Chengzhi Zhang. Analysis of Knowledge Flow Based on Academic Social Networks:
A Case Study of
[J]. 数据分析与知识发现, 2019, 3(4): 107-116.
  Copyright © 2016 Data Analysis and Knowledge Discovery   Tel/Fax:(010)82626611-6626,82624938