面向不同用户群体的社交媒体台风舆情演化分析及对比研究

doi:10.12082/dqxxkx.2021.210065

摘要/Abstract

摘要：

社交媒体数据可以为台风灾害追踪、灾时救援和灾情评估提供及时有效的信息。现有研究常采用主题建模和情感分析等技术对台风期间社交媒体平台（如新浪微博等）舆论话题和情感变化进行研究。在省域范围内以小时为时间粒度的多维度有效性论证尚有欠缺,且在舆情分析时未能区分用户群体差异。本文以台风“利奇马”为例,在浙江省域范围内,以新浪微博数据为研究对象,首先从词频分析、台风关注度时空变化以及特定灾害事件响应3个角度探讨了微博数据对台风灾情响应的有效性;其次采用隐含狄利克雷分布（Latent Dirichlet Allocation,LDA）主题模型技术挖掘微博文本主题信息,并根据Louvain算法对主题社团进行划分;然后开发了一种基于自定义情感词典的情感分析方法用于情感指数计算,与SnowNLP相比情感倾向性预测精度得到了提高;最后分析了台风期间官方和民众在新浪微博平台上的话题关注以及情感演变差异。结果表明：① 在省级范围内,微博数据能有效反映台风动态和灾害时空分布;② 台风事件微博文本的主题变化反映了灾情不同阶段舆论关注点的动态变化;③ 官方微博文本比民众微博文本具有更明确的主题社团结构;④ 台风事件相关微博文本中的消极情绪在台风登陆后显著增加,其中民众微博文本对台风灾害的情绪响应更及时,官方微博文本中的情感表达始终相对积极。

关键词: 新浪微博, 台风, 舆情, 时空分析, 主题模型, 情感分析, 用户群体差异

Abstract:

Social media has been successfully applied to typhoon monitoring, on-site rescue, and disaster loss assessment. Preview studies mostly utilized topic modeling and sentiment analysis technique to analyze the focus of public opinion and sentiment evolution in the social media platform during the typhoon period. However, the existing studies were usually conducted at large spatial scales and long time spans. Moreover, the difference in behavior pattern among user groups was ignored. Firstly, a case study of Typhoon Lekima was implemented for verifying the effectiveness of microblog's response to typhoon disaster in Zhejiang province from three perspectives: word frequency, spatiotemporal change of public attention to typhoon, and public response to specific events. Secondly, the Latent Dirichlet Allocation (LDA) topic model was adopted to mine the text topics, whose community structure were divided by Louvain algorithm. Thirdly, a custom emotion dictionary was developed to calculate the sentiment index, and subsequently compared with SnowNLP in sentiment polarity prediction. Finally, we investigated the difference between official microblogs and public microblogs in topic concern and sentiment evolution. The results indicated that microblogs were capable of tracking typhoon dynamics and reflecting the spatiotemporal distribution of hazards within the provincial region. The LDA model result showed that the percentage of microblogs on public dynamics topic was large in days and small in nights; the percentage of microblogs on warning topic was on a downward trend; the disaster event rose significantly after typhoon landed; and the peak of that on rescue activities appeared in the late period of typhoon. The topic of official microblog had a clearer community structure than the public microblog, but this characteristic may be blurry when mixing the microblogs from two groups. The negative emotion on Sina Weibo significantly deepened in the typhoon landing period, and the public had a more timely emotional response to typhoon disasters, while the sentiment index of official microblog was always higher.

Key words: Sina Weibo, typhoon, public opinion, spatiotemporal analysis, topic model, sentiment analysis, different user groups

金城, 吴文渊, 陈柏儒, 杨续超. 面向不同用户群体的社交媒体台风舆情演化分析及对比研究[J]. 地球信息科学学报, 2021, 23(12): 2174-2186.DOI:10.12082/dqxxkx.2021.210065

JIN Cheng, WU Wenyuan, CHEN Bairu, YANG Xuchao. Analysis and Comparative Study of the Evolution of Public Opinion on Social Media during Typhoon for Different User Groups[J]. Journal of Geo-information Science, 2021, 23(12): 2174-2186.DOI:10.12082/dqxxkx.2021.210065

图/表 11

表1

图1

图2

图3

图4

图5

图6

图7

表2

图8

图9

参考文献 32

[1]	李钢, 邱新法, 张眉, 等. 浙江省台风灾害直接经济损失评估模型[J]. 热带地理, 2014, 34(2):178-183.
	[ Li G, Qiu X F, Zhang M, et al. Direct economic losses assessment of typhoon disaster in Zhejiang Province[J]. Tropical Geography, 2014, 34(2):178-183. ]
[2]	郭云霞, 侯一筠, 齐鹏. 中国东南沿海区域台风数值模拟与危险性分析[J]. 海洋科学, 2020, 44(4):1-12.
	[ Guo Y X, Hou Y J, Qi P. Typhoon wind numerical simulation and risk analysis for southeast coastal region of China[J]. Marine Sciences, 2020, 44(4):1-12. ]
[3]	Li Z L, Wang C Z, Emrich C T, et al. A novel approach to leveraging social media for rapid flood mapping: A case study of the 2015 South Carolina floods[J]. Cartography and Geographic Information Science, 2018, 45(2):97-110. doi: 10.1080/15230406.2016.1271356
[4]	Hao H, Wang Y. Leveraging multimodal social media data for rapid disaster damage assessment[J]. International Journal of Disaster Risk Reduction, 2020, 51:1-13.
[5]	Erdelj M, Król M, Natalizio E. Wireless sensor networks and multi-UAV systems for natural disaster management[J]. Computer Networks, 2017, 124:72-86. doi: 10.1016/j.comnet.2017.05.021
[6]	Guan X Y, Chen C. Using social media data to understand and assess disasters[J]. Natural Hazards, 2014, 74(2):837-850. doi: 10.1007/s11069-014-1217-1
[7]	Kryvasheyeu Y, Chen 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]	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
[9]	Huang Q, Cervone G, Jing D, et al. DisasterMapper: A CyberGIS framework for disaster management using social media data[C]// Proceedings of the 4^th International ACM SIGSPATIAL Workshop on Analytics for Big Geospatial Data. ACM, 2015:1-6.
[10]	Huang Q, Cervone G, Zhang G. A cloud-enabled automatic disaster analysis system of multi-sourced data streams: An example synthesizing social media, remote sensing and Wikipedia data[J]. Computers, Environment and Urban Systems, 2017, 66(1):23-37. doi: 10.1016/j.compenvurbsys.2017.06.004
[11]	Neppalli V K, Caragea C, Squicciarini A, et al. Sentiment analysis during Hurricane Sandy in emergency response[J]. International Journal of Disaster Risk Reduction, 2017, 21:213-222. doi: 10.1016/j.ijdrr.2016.12.011
[12]	Chen S, Mao J, Li G, et al. Uncovering sentiment and retweet patterns of disaster-related tweets from a spatiotemporal perspective: A case study of Hurricane Harvey[J]. Telematics and Informatics, 2020, 47:1-18.
[13]	Alam F, Ofli F, Imran M. Descriptive and visual summaries of disaster events using artificial intelligence techniques: Case studies of Hurricanes Harvey, Irma, and Maria[J]. Behaviour & Information Technology, 2020, 39(3):288-318.
[14]	陈梓, 高涛, 罗年学, 等. 反映自然灾害时空分布的社交媒体有效性探讨[J]. 测绘科学, 2017, 42(8):44-48,129.
	[ Chen Z, Gao T, Luo N X, et al. Empirical discussion on relation between realistic disasters and social media data[J]. Science of Surveying and Mapping, 2017, 42(8):44-48,129. ]
[15]	杨腾飞, 解吉波, 李振宇, 等. 微博中蕴含台风灾害损失信息识别和分类方法[J]. 地球信息科学学报, 2018, 20(7):906-917. doi: 10.12082/dqxxkx.2018.180062
	[ Yang T F, Xie J B, Li Z Y, et al. A method of typhoon disaster loss identification and classification using micro-blog information[J]. Journal of Geo-Information Science, 2018, 20(7):906-917. ]
[16]	梁春阳, 林广发, 张明锋, 等. 社交媒体数据对反映台风灾害时空分布的有效性研究[J]. 地球信息科学学报, 2018, 20(6):807-816. doi: 10.12082/dqxxkx.2018.180022.
	[ Liang C Y, Lin G F, Zhang M F, et al. Assessing the Effectiveness of Social Media Data in Mapping the Distribution of Typhoon Disasters[J]. Journal of Geo-information Science, 2018, 20(6):807-816. ]
[17]	张岩, 李英冰和郑翔.基于微博数据的台风“山竹”舆情演化时空分析[J]. 山东大学学报(工学版), 2020, 50(5):118-126.
	[ Zhang Y, Li Y B, Zheng X. Spatial and temporal analysis of network public opinion evolution of typhoon"Mangkhut"based on Weibo data[J]. Journal of Shandong University(Engineering Science), 2020, 50(5):118-126. ]
[18]	Chen J T, She J. An analysis of verifications in microblogging social networks-Sina Weibo[C]// Proceedings of the 32nd IEEE International Conference on Distributed Computing Systems Workshops (ICDCSW). IEEE, 2012:147-154.
[19]	王晰巍, 张柳, 黄博, 等. 基于LDA的微博用户主题图谱构建及实证研究——以“埃航空难”为例[J]. 数据分析与知识发现, 2020, 4(10):47-57.
	[ Wang X, Zhang L, Huang B, et al. Constructing topic graph for Weibo users based on LDA: case study of“Egypt Air Disaster”[J]. Data Analysis and Knowledge Discovery, 2020, 4(10):47-57. ]
[20]	Graham M W, Avery E J, Park S. The role of social media in local government crisis communications[J]. Public Relations Review, 2015, 41(3):386-394. doi: 10.1016/j.pubrev.2015.02.001
[21]	Chatfield A T, Reddick C G. All hands on deck to tweet #sandy: Networked governance of citizen coproduction in turbulent times[J]. Government Information Quarterly, 2018, 35(2):259-272. doi: 10.1016/j.giq.2017.09.004
[22]	Kogan M, Palen L, Anderson K M. Think local, retweet global: retweeting by the geographically- vulnerable during Hurricane Sandy[C]// Proceedings of the 18th ACM Conference on Computer Supported Cooperative Work & Social Computing. ACM, 2015:981-993.
[23]	应急管理部救灾和物资保障司. 应急管理部公布2019年全国十大自然灾害[EB/OL]. https://www.mem.gov.cn/xw/bndt/202001/t20200112_343410.shtml, 2020-01-12.
	[ Disaster Relief and Material Support Division, Ministry of Emergency Management of the People's Republic of China. Ministry of Emergency Management announced 10 major natural disasters in 2019[EB/OL]. https://www.mem.gov.cn/xw/bndt/202001/t20200112_343410.shtml, 2020-01-12. ]
[24]	人民网舆情数据中心. 2019年政务指数·微博影响力报告[EB/OL]. http://yuqing.people.com.cn/NMediaFile/2020/0117/MAIN202001171722000261251830504.pdf,2020-01-17.
	[Public Opinion Data Centre of People's Daily Online. Government affairs index microblog influence report 2019[EB/OL]. http://yuqing.people.com.cn/NMediaFile/2020/0117/MAIN202001171722000261251830504.pdf,2020-01-17. ]
[25]	Blei D M, Ng A Y, Jordan M I. Latent dirichlet allocation[J]. Journal of machine Learning research, 2003, 3:993-1022.
[26]	方东昊. 基于LDA的微博短文本分类技术的研究与实现[D]. 沈阳:东北大学, 2011.
	[ Fang D H. Study and implementation for Microblog's short text classification based on LDA[D]. Shenyang: Northeastern University, 2011. ]
[27]	王鹏, 高铖, 陈晓美. 基于LDA模型的文本聚类研究[J]. 情报科学, 2015, 33(1):63-68.
	[ Wang P, Gao C, Chen X M. Research on LDA model based on text clustering[J]. Information Science, 2015, 33(1):63-68. ]
[28]	Xiao H, Stibor T. Efficient collapsed gibbs sampling for latent dirichlet allocation[C]. Proceedings of 2^nd Asian Conference on Machine Learning, 2010.
[29]	吴祖峰, 王鹏飞, 秦志光, 等. 改进的Louvain社团划分算法[J]. 电子科技大学学报, 2013, 42(1):105-108.
	[ Wu Z F, Wang P F, Qin Z G, et al. Improved Algorithm of Louvain Communities Dipartition[J]. Journal of University of Electronic Science and Technology of China, 2013, 42(1):105-108. ]
[30]	Blondel V D, Guillaume J L, Lambiotte R, et al. Fast unfolding of communities in large networks[J]. Journal of Statistical Mechanics: Theory and Experiment, 2008, 2008(10):1-12.
[31]	黄天诚. 基于图着色的并行Louvain社区发现算法研究[D]. 长春:吉林大学, 2016.
	[ Huang T C. Design of parallel Louvain method for community detection algorithm based on graph coloring[D]. Changchun: Jilin University, 2016. ]
[32]	Chen C, Chen J, Shi C. Research on credit evaluation model of online store based on SnowNLP[C]// Proceedings of the 3rd International Conference on Advances in Energy and Environment Research (ICAEER). EDP Sciences, 2018:1-4.

台风编号	台风名称	搜集时段	有效微博数量/条
1904	木恩(Mun)	2019-07-02 00:00—2019-07-05 00:00	303
1907	韦帕(Wipha)	2019-07-31 00:00—2019-08-03 00:00	369
1909	利奇马(Lekima)	2019-08-09 00:00—2019-08-12 00:00	72 514
1911	白鹿(Bailu)	2019-08-24 00:00—2019-08-27 00:00	1404
1914	剑鱼(Kajiki)	2019-09-01 00:00—2019-09-04 00:00	396
1919	海贝思(Hagibis)	2019-10-11 00:00—2019-10-14 00:00	784

	基于情感词典			SnowNLP
	积极	中性	消极	积极	中性	消极
Precision	0.873	0.713	0.835	0.472	0.348	0.547
Recall	0.785	0.760	0.881	0.608	0.204	0.517
F-measure	0.826	0.736	0.857	0.532	0.257	0.532