气候变化背景下融合社交媒体情感与多源数据的洪涝损失估算

doi:10.12006/j.issn.1673-1719.2023.203

气候变化研究进展 ›› 2024, Vol. 20 ›› Issue (1): 26-36.doi: 10.12006/j.issn.1673-1719.2023.203

气候变化背景下融合社交媒体情感与多源数据的洪涝损失估算

武志霞¹^,²^,³(), 郑霞忠¹^,², 陈一君³, 黄山⁴, 胡文莉³, 段晨斐¹^,²()

1 三峡大学水电工程施工与管理湖北省重点实验室，宜昌 443002
2 三峡大学水利与环境学院，宜昌 443002
3 四川轻化工大学管理学院，自贡 643000
4 宜宾市翠屏区市政建设工程中心，宜宾 644000

收稿日期:2023-09-14 修回日期:2023-10-11 出版日期:2024-01-30 发布日期:2023-12-28
通讯作者: 段晨斐，男，博士研究生，202108150011016@ctgu.edu.cn
作者简介:武志霞，女，博士研究生，wzx55233@163.com
基金资助:
国家自然科学基金面上项目(51878385);成渝地区双城经济圈川南发展研究院项目(CYQCNY20223);川酒发展研究中心项目(CJY23-12)

Flood loss estimation by integrating social media sentiment and multi-source data under climate change background

WU Zhi-Xia¹^,²^,³(), ZHENG Xia-Zhong¹^,², CHEN Yi-Jun³, HUANG Shan⁴, HU Wen-Li³, DUAN Chen-Fei¹^,²()

1 Hubei Key Laboratory of Hydropower Engineering Construction and Management, China Three Gorges University, Yichang 443002, China
2 College of Hydraulic & Environmental Engineering, China Three Gorges University, Yichang 443002, China
3 College of Management, Sichuan University of Science & Engineering, Zigong 643000, China
4 Municipal Construction Engineering Center of Cuiping District, Yibin 644000, China

Received:2023-09-14 Revised:2023-10-11 Online:2024-01-30 Published:2023-12-28

摘要/Abstract

摘要：

提取2021年7月10日—2023年4月10日新浪微博的洪涝灾害文本，基于朴素贝叶斯算法实现暴雨洪涝情感分析，构建了一种融合核心致灾因子、承灾载体和社交媒体实时数据的洪涝灾损估算（ISFRD）模型。结果表明：在社交媒体中，暴雨洪涝灾害的情感峰值主要集中在6—8月，峰值变化和洪涝灾害热点事件讨论具有强同步关系；洪灾期间情感波动变化，洪涝损失与平均情感值具有反向关系；ISFRD洪涝灾损模型可以有效评估省（市）级尺度、不同受灾程度的暴雨洪涝事件，估算结果精度较高（平均准确率>90%，MAE=27.04，RMSE=45.26）。在日益复杂的气候环境下，该模型可为洪涝灾损快速厘定、防灾减灾和舆论引导提供一定参考。

关键词: 社交媒体, 情感分析, 多源数据, ISFRD模型, 灾损估算

Abstract:

Based on social media text data, the flood loss estimation model (ISFRD) was constructed that combines the core factors causing flooding, disaster-bearing vectors and real-time sentiment data. First, text information related to flooding on the Sina Weibo platform was extracted based on natural language processing technology to achieve data preprocessing. Geolocation enrichment was then performed and the validity of the Weibo data was verified using the example of the exceptionally heavy rainfall in Henan province. Afterwards, loss estimation was made for several flood events in China based on a multi-source set of factors such as flood causation and sentiment, and the accuracy of the loss estimation was verified against the actual losses. The results are as follows. (1) In social media, the peak sentiment mutation points of heavy rainfall and flooding are mainly concentrated in June to August each year. Also, the peak sentiment change and the discussion of hot flood events have a strong synchronous relationship. (2) Flood losses have an inverse relationship with average sentiment, i.e., the lower the average sentiment value is, the more serious the disaster damage is in general. (3) The ISFRD flood damage model can effectively assess heavy rainfall and flooding events at the provincial (municipal) scale with different degrees of damage, and the estimation results have high accuracy (average accuracy>90%, MAE=27.04, RMSE=45.26). Under the increasingly complex climate environment, the model can provide a certain reference for rapid determination of flood damage, disaster prevention and mitigation, and public opinion guidance.

Key words: Social media, Sentiment analysis, Multi-source data, ISFRD model, Loss estimation

武志霞, 郑霞忠, 陈一君, 黄山, 胡文莉, 段晨斐. 气候变化背景下融合社交媒体情感与多源数据的洪涝损失估算[J]. 气候变化研究进展, 2024, 20(1): 26-36.

WU Zhi-Xia, ZHENG Xia-Zhong, CHEN Yi-Jun, HUANG Shan, HU Wen-Li, DUAN Chen-Fei. Flood loss estimation by integrating social media sentiment and multi-source data under climate change background[J]. Climate Change Research, 2024, 20(1): 26-36.

图/表 9

图1 研究框架

Fig. 1 Research framework

表1 中国气象部门降水等级

Table 1 China meteorological department precipitation level

表2 分词处理示例

Table 2 Example of word segmentation processing

图2 微博词云图

Fig. 2 Weibo word cloud

图3 洪涝相关微博的情感变化趋势

Fig. 3 Floods-related Weibo sentiment trend

图4 河南7·20暴雨中洪涝灾害的情感分布注：因海南、吉林、台湾、西藏、香港、新疆等地区发文量不足5篇，不足以判断该地区公众对洪涝灾害的态度，分析时略。

Fig. 4 Sentiment distribution of flood disaster in the 7·20 rainstorm in Henan province

表3 中国部分洪涝灾害事件的灾情数据

Table 3 Disaster data of some flooding events in China

表4 基于ISFRD的洪涝灾损估算结果验证

Table 4 Validation of the ISFRD model results

图5 洪涝灾损估算值对比图注：图中5组数据从左至右分别对应四川7·11暴雨、湖北8·11暴雨、陕西8·20暴雨、郑州市7·20暴雨和河南7·20暴雨事件。

Fig. 5 Comparison of estimated flood losses

参考文献 38

[1]	Su X, Shao W, Liu J, et al. Dynamic assessment of the impact of flood disaster on economy and population under extreme rainstorm events[J]. Remote Sensing, 2021, 13 (19): 3924 doi: 10.3390/rs13193924 URL
[2]	Jeroen A, Wouter B, Kerry E, et al. Evaluating flood resilience strategies for coastal megacities[J]. Science, 2014, 344 (6183): 473-475 doi: 10.1126/science.1248222 pmid: 24786064
[3]	Wu Z X, Zheng X Z, Chen Y J, et al. Urban flood loss assessment and index insurance compensation estimation by integrating remote sensing and rainfall multi-source data: a case study of the 2021 Henan rainstorm[J]. Sustainability, 2023, 15: 11639 doi: 10.3390/su151511639 URL
[4]	Willner S N, Otto C, Levermann A. Global economic response to river floods[J]. Nature Climate Change, 2018 (8): 594-598
[5]	胡恒智, 顾婷婷, 田展. 气候变化背景下的洪涝风险稳健决策方法评述[J]. 气候变化研究进展, 2018, 14 (1): 77-85.
	Hu H Z, Gu T T, Tian Z. A review of robust decision-making methods for flood risk in the context of climate change[J]. Climate Change Research, 2018, 14 (1): 77-85 (in Chinese)
[6]	谭玲, 姚帏之, 李廉水, 等. 城市暴雨洪涝灾害直接经济损失的文献计量分析[J]. 灾害学, 2020, 35 (3): 179-185.
	Tan L, Yao W Z, Li L S, et al. Direct economic loss assessment of urban storm flood disasters based on bibliometric analysis[J]. Journal of Catastrophology, 2020, 35 (3): 179-185 (in Chinese)
[7]	Yury K, Haohui C, Esteban M, et al. Performance of social network sensors during hurricane sandy[J]. Plos One, 2015, 10 (2): e0117288 doi: 10.1371/journal.pone.0117288 URL
[8]	Zheng X Z, Duan C F, Chen Y, et al. Disaster loss calculation method of urban flood bimodal data fusion based on remote sensing and text[J]. Journal of Hydrology: Regional Studies, 2023, 47: 101410 doi: 10.1016/j.ejrh.2023.101410 URL
[9]	闫绪娴, 刘霁, 陈秋霏, 等. 话题共振视角下自然灾害次生舆情形成路径研究[J]. 灾害学, 2023, 38 (4): 1-9.
	Yan X X, Liu J, Chen Q F, et al. The study on the formation path of secondary public opinion of natural disasters from the perspective of topic resonance[J]. Journal of Catastrophology, 2023, 38 (4): 1-9 (in Chinese)
[10]	Yang T, Xie J, Li G. A social media-based dataset of typhoon disasters, 2017[J]. China Scientific Data, 2018, 3 (2): 51-61
[11]	Alfarrarjeh A, Agrawal S, Kim S, et al. Geo-Spatial multimedia sentiment analysis in disasters[C]// 2017 IEEE International Conference on Data Science and Advanced Analytics (DSAA). IEEE, 2017
[12]	Shoyama K, Cui Q, Hanashima M, et al. Emergency flood detection using multiple information sources: integrated analysis of natural hazard monitoring and social media data[J]. Science of the Total Environment, 2021, 767: 144371 doi: 10.1016/j.scitotenv.2020.144371 URL
[13]	Li S, Wang Y, Huang H, et al. Study on typhoon disaster assessment by mining data from social media based on artificial neural network[J]. Natural Hazards, 2023, 116: 2069-2089
[14]	Kitazawa K, Hale S A. Social media and early warning systems for natural disasters: a case study of typhoon Etau in Japan[J]. International Journal of Disaster Risk Reduction, 2021, 52: 101926 doi: 10.1016/j.ijdrr.2020.101926 URL
[15]	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 URL
[16]	Shan S, Zhao F, Wei Y. Real-time assessment of human loss in disasters based on social media mining and the truth discovery algorithm[J]. International Journal of Disaster Risk Reduction, 2021, 62 (3): 102418 doi: 10.1016/j.ijdrr.2021.102418 URL
[17]	Allaire M C. Disaster loss and social media: can online information increase flood resilience?[J]. Water Resources Research, 2016, 52: 7408-7423 doi: 10.1002/wrcr.v52.9 URL
[18]	Shan S, Zhao F, Wei Y, 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 URL
[19]	Dargin J, Fan C, Mostafavi A. Vulnerable populations and social media use in disasters: uncovering the digital divide in three major U.S. hurricanes[J]. International Journal of Disaster Risk Reduction, 2021, 54 (4): 102043 doi: 10.1016/j.ijdrr.2021.102043 URL
[20]	Fan C, Esparza M, Dargin J, et al. Spatial biases in crowdsourced data: social media content attention concentrates on populous areas in disasters[J]. Computers, Environment and Urban Systems, 2020, 83 (9): 101514 doi: 10.1016/j.compenvurbsys.2020.101514 URL
[21]	Duan C F, Zheng X Z, Jin L H, et al. Study on the remote sensing spectral method for disaster loss inversion in urban flood areas[J]. Water, 2022, 14 (14): 2165 doi: 10.3390/w14142165 URL
[22]	Tellman B, Lall U, Islam A K, et al. Regional index insurance using satellite-based fractional flooded area[J]. Earth’s Future, 2022, 10 (3): e2021EF002418
[23]	Rizwan M, Anjum L, Mehmood Q, et al. Daily maximum rainfall estimation by best-fit probability distribution in the source region of Indus River[J]. Theoretical and Applied Climatology, 2022, 151: 1171-1183 doi: 10.1007/s00704-022-04334-8
[24]	Donner W, Rodríguez H. Population composition, migration and inequality: the influence of demographic changes on disaster risk and vulnerability[J]. Social Forces, 2008, 87 (2): 1089-1114 doi: 10.1353/sof.0.0141 URL
[25]	龚艳冰, 向林, 刘高峰. 基于高斯过程回归模型的洪涝灾害损失预测研究: 以重庆市为例[J]. 长江流域资源与环境, 2019, 28 (6): 1502-1510.
	Gong Y B, Xiang L, Liu G F. Study on flood disaster loss prediction based on Gaussian process regression model: a case study of Chongqing city[J]. Resources and Environment in the Yangtze Basin, 2019, 28 (6): 1502-1510 (in Chinese)
[26]	李绍攀, 赵飞, 周义棋, 等. 基于微博数据的台风灾害舆情分析与灾害损失估计[J]. 清华大学学报(自然科学版), 2022, 62 (1): 43-51.
	Li S P, Zhao F, Zhou Y Q, et al. Analysis of public opinion and disaster loss estimates from typhoons based on micro-blog data[J]. Journal of Tsinghua University (Science and Technology), 2022, 62 (1): 43-51 (in Chinese)
[27]	Xu B, Guo X, Ye Y, et al. An improved random forest classifier for text categorization[J]. Journal of Computers, 2012, 7 (12): 2913-2920
[28]	郑苏晋, 郭海若, 宋姝凝, 等. 社交媒体数据对台风灾害的预警研究: 以利奇马台风为例[J]. 管理评论, 2021, 33 (10): 340-352.
	Zheng S J, Guo H R, Song S N, et al. Research on early warning of typhoon disasters based on social media data: a case study of typhoon Lekima[J]. Management Review, 2021, 33 (10): 340-352 (in Chinese)
[29]	Turney P D. Learning algorithms for key phrase extraction[J]. Information Retrieval, 2000, 2 (4): 303-336 doi: 10.1023/A:1009976227802 URL
[30]	Willmott C, Matsuura K. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance[J]. Climate Research, 2005, 30 (1): 79-82 doi: 10.3354/cr030079 URL
[31]	Kogan M, Palen L, Anderson K M. Think local, retweet global: retweeting by the geographically-vulnerable during hurricane sandy[J]. Association for Computing Machinery, 2015, 15 (1): 981-993
[32]	陈兴蜀, 常天祐, 王海舟, 等. 基于微博数据的“新冠肺炎疫情”舆情演化时空分析[J]. 四川大学学报(自然科学版), 2020, 57 (2): 409-416.
	Chen X S, Chang T Y, Wang H Z, et al. Spatial and temporal analysis on public opinion evolution of epidemic situation about novel coronavirus pneumonia based on micro-blog data[J]. Journal of Sichuan University (Natural Science Edition), 2020, 57 (2): 409-416 (in Chinese)
[33]	Wang Y, Ruan S, Wang T, et al. Rapid estimation of an earthquake impact area using a spatial logistic growth model based on social media data[J]. International Journal of Digital Earth, 2018, 12 (11): 1-20 doi: 10.1080/17538947.2018.1559481 URL
[34]	耿树丰, 任嘉义, 杨俊, 等. 局地气候区视角下的城市热环境研究[J]. 生态学报, 2022, 42 (6): 2221-2227.
	Geng S F, Ren J Y, Yang J, et al. Exploration of urban thermal environment based on local climate zone[J]. Acta Ecologica Sinica, 2022, 42 (6): 2221-2227 (in Chinese)
[35]	赵宗慈, 罗勇, 黄建斌. 全球变暖与旱涝事件[J]. 气候变化研究进展, 2023, 19 (2): 258-262.
	Zhao Z C, Luo Y, Huang J B. Global warming and floods/droughts[J]. Climate Change Research, 2023, 19 (2): 258-262 (in Chinese)
[36]	金城, 吴文渊, 陈柏儒, 等. 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 C, Wu W Y, Chen B R, et al. 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 (in Chinese)
[37]	Watson H, Finn R L, Wadhwa K. Organizational and societal impacts of big data in crisis management[J]. Journal of Contingencies and Crisis Management, 2017, 25: 15-22 doi: 10.1111/jccm.2017.25.issue-1 URL
[38]	Karami A, Shah V, Vaezi R, et al. Twitter speaks: a case of national disaster situational awareness[J]. Journal of Information Science, 2019, 46: 313-324 doi: 10.1177/0165551519828620 URL

气候变化背景下融合社交媒体情感与多源数据的洪涝损失估算

Flood loss estimation by integrating social media sentiment and multi-source data under climate change background

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 38

相关文章 1

编辑推荐

Metrics

本文评价