Journal of Shandong University(Engineering Science) ›› 2020, Vol. 50 ›› Issue (5): 118-126.doi: 10.6040/j.issn.1672-3961.0.2019.371

Previous Articles    

Spatial and temporal analysis of network public opinion evolution of typhoon “Mangkhut” based on Weibo data

ZHANG Yan1,2, LI Yingbing1*, ZHENG Xiang3   

  1. 1. School of Geodesy and Geomatics, Wuhan University, Wuhan 430079, Hubei, China;
    2. State Key Laboratory of Information Engineering in Surveging, Mapping and Remote Sensing, Wuhan 430079, Hubei, China;
    3. School of Information Management, Wuhan University, Wuhan 430072, Hubei, China
  • Published:2020-10-19

Abstract: Internet public opinion was the sum of the public various emotions, attitudes and opinions on related topics. This paper applied the sentiment analysis model, dynamic evolution model, topic clustering model, network community model and geographic visualization technology to the typhoon disaster assessment. This research fully illustrated how the public opinion on typhoon “Mangkhut” evolved by analyzing the 25 798 Weibo related from the two perspectives of emotional value and discussion heat. By utilizing LDA clustering method the negative impacts of typhoon “Mangkhut”'s landing and “Hunan toll station event” on public sentiment were found. After collecting the geographical location information of those typhoon “Mangkhut” related Weibo, a network-community model of 21 cities in Guangdong province was established and the model tested the ability to explore the affected cities through such indicators as users' sentiments, city word frequency, users' location, and network node activity. Spatial interpolation was performed based on the 24 h maximum rainfall data from 38 meteorological stations in Guangdong province. Precipitation was mainly concentrated in the southern part of Guangdong. Heavy rains occurred in Yangjiang City, which caused severe flooding and the lowest emotional value.

Key words: natural language processing, spatial analysis, community analysis, Sina Weibo, public safety

CLC Number: 

  • TU984.116
[1] 刘哲, 张鹏, 刘南江,等. “一带一路”中国重点区域自然灾害特征分析[J]. 灾害学,2018,33(4):65-71. LIU Zhe, ZHANG Peng, LIU Nanjiang, et al. Characteristics of natural disasters in key regions of One Belt One Road initiative[J]. Disaster Science, 2018, 33(4):65-71.
[2] NING Xiaodong, YAO Lina, WANG Xianzhi, et al. Calling for response: automatically distinguishing situation-aware tweets during crises[C] //The 13th International Conference on Advanced Data Mining and Applications. Singapore, Singapore: Springer, 2017.
[3] NAIR M R, RAMYA G R, SIVAKUMAR P B. Usage and analysis of Twitter during 2015 Chennai flood towards disaster management[C] //7th International Conference on Advances in Computing & Communications(ICACC-2017). Cochin, India: Elsevier, 2017.
[4] ALFARRARJEH A, AGRAWAL S, KIM S H, et al. Geo-spatial multimedia sentiment analysis in disasters[C] //The 4th IEEE International Conference on Data Science and Advanced Analytics 2017. Tokyo, Japan: IEEE, 2017.
[5] 唐晓波,向坤. 基于LDA模型和微博热度的热点挖掘[J]. 图书情报工作,2014,58(5):58-63. TANG Xiaobo, XIANG Kun. Hotspot mining based on LDA model and microblog heat[J]. Library and Information Service, 2014, 58(5):58-63.
[6] 阮光册. 基于LDA的网络评论主题发现研究[J]. 情报杂志,2014,33(3):161-164. RUAN Guangce. Topic extraction research of net reviews based on Latent Dirichlet Allocation[J]. Journal of Intelligence, 2014, 33(3):161-164.
[7] CHOI S, BAE B. The real-time monitoring system of social big data for disaster management[M]. Berlin, Germany: Springer, 2015.
[8] 白华,林勋国. 基于中文短文本分类的社交媒体灾害事件检测系统研究[J]. 灾害学,2016,31(2):19-23. BAI Hua, LIN Xunguo. Research on social media disaster incident detection system based on Chinese short text classification[J]. Disaster Science, 2016, 31(2):19-23.
[9] 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. CHEN Zi, GAO Tao, LUO Nianxue, et al. Discussion on the effectiveness of social media reflecting the spatial and temporal distribution of natural disasters[J]. Surveying Science, 2017, 42(8):44-48.
[10] 王心瑶,郝艳华,吴群红,等. 社交媒体环境下H7N9事件网络舆情演变与比较分析[J]. 中国公共卫生,2018,34(9):1232-1236. WANG Xinyao, HAO Yanhua, WU Qunhong, et al. Evolution and comparative analysis of H7N9 event network in social media environment[J]. China Public Health, 2018, 34(9):1232-1236.
[11] 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. LIANG Chunyang, LIN Guangfa, ZHANG Mingfeng, et al. Effectiveness of social media data to reflect the temporal and spatial distribution of typhoon disasters[J]. Journal of Earth Information Science, 2018,20(6):807-816.
[12] BLEI D M, NG A Y, JORDAN M I. Latent Dirichlet allocation[J]. Journal of Machine Learning Research, 2003, 3(4/5):993-1022.
[13] GRIFFITHS T L, STEYVERS M. Finding scientific topics[J]. Proc Natl Acad Sci U S A, 2004, 101(Suppl 1):5228-5235.
[14] CAO Juan, TIAN Xia, LI Jintao, et al. A density-based method for adaptive LDA model selection[J]. Neuro Computing, 2009, 72(7):1775-1781.
[15] 周咏梅,阳爱民,林江豪. 中文微博情感词典构建方法[J]. 山东大学学报(工学版), 2014, 44(3):36-40. ZHOU Yongmei, YANG Aimin, LIN Jianghao. Construction method of Chinese Weibo emotional dictionary[J]. Journal of Shandong University(Engineering Science), 2014, 44(3):36-40.
[16] 朱嫣岚,闵锦,周雅倩,等. 基于HowNet的词汇语义倾向计算[J]. 中文信息学报,2006(1):14-20. ZHU Yanlan, MIN Jin, ZHOU Yaqian, et al. Calculation of lexical semantic tendency based on HowNet[J]. Journal of Chinese Information Processing, 2006(1):14-20.
[17] 杨振山,蔡建明. 空间统计学进展及其在经济地理研究中的应用[J]. 地理科学进展, 2010,29(6):757-768. YANG Zhenshan, CAI Jianming. Progress in spatial statistics and its application in economic geography research[J]. Progress in Geography, 2010, 29(6): 757-768.
[18] NEWMAN M. Detecting community structure in networks[J]. European Physical Journal B, 2004, 38(2):321-330.
[19] 李沐南. Louvain算法在社区挖掘中的研究与实现[D].北京:中国石油大学(北京),2016. LI Munan. Research and implementation of Louvain algorithm in community mining[D]. Beijing: China University of Petroleum(Beijing), 2016.
[20] 赵燕慧,路紫,张秋娈. 多类型微博舆情时空分布关系的差异性及其地理规则[J]. 人文地理,2018,33(1):61-69. ZHAO Yanhui, LU Zi, ZHANG Qiuluan. The differences of temporal and spatial distribution relationships of multi-type Weibo and their geographical rules[J]. Human Geography, 2018, 33(1):61-69.
[21] 李静. 基于LDA的微博灾害信息聚合[D].武汉:武汉大学,2018. LI Jing. LDA-based microblog disaster information aggregation [D]. Wuhan: Wuhan University, 2018.
[22] SUN Penggang, GAO Lin, HAN Shanshan. Identification of overlapping and non-overlapping community structure by fuzzy clustering in complex networks[J]. Information Sciences, 2010, 181(6):1060-1071.
[23] 刘超然. 在线新闻网民评论情感倾向性分析及可视化研究[D].哈尔滨:哈尔滨工业大学,2018. LIU Chaoran. Online news netizens comment on emotional orientation analysis and visualization[D]. Harbin: Harbin Institute of Technology, 2018.
[24] 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. YANG Tengfei, XIE Jibo, LI Zhenyu, et al. Identification and classification of typhoon disaster loss information in Weibo[J]. Journal of Earth Sciences, 2018, 20(7):906-917.
[25] 王祎珺,张晖,李波,等. 一种基于话题演化的意见领袖发现方法[J]. 山东大学学报(工学版),2016,46(2):35-42. WANG Weijun, ZHANG Hui, LI Bo, et al. A method for opinion leader discovery based on topic evolution[J]. Journal of Shandong University(Engineering Science), 2016, 46(2):35-42.
[1] Haijun ZHANG,Yinghui CHEN. Semantic analysis and vectorization for intelligent detection of big data cross-site scripting attacks [J]. Journal of Shandong University(Engineering Science), 2020, 50(2): 118-128.
[2] XIE Zhifeng, WU Jiaping, MA Lizhuang. Chinese financial news classification method based on convolutional neural network [J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2018, 48(3): 34-39.
[3] DONG Ai-Feng, DIAO Ge-Ji, SCHOMMER Christoph. A fingerprint engine for author profiling [J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2009, 39(5): 27-31.
Full text



No Suggested Reading articles found!