Abstract：Social media data, as a type of spatiotemporal meta data, possesses real-time and location-based characteristics, and has been widely utilized in flood risk management abroad in recent years. However, the research on this data type in flood risk management in China is less, and related applications are limited. Through reviewing the research on flood disasters based on social media data both domestically and internationally, this paper explores methods for extracting and analyzing flood risk information. It also identifies directions for applying this information in flood risk management, including flood disaster monitoring and early warning, spatiotemporal distribution of disasters situation, sentiment analysis, response behavior analysis,disaster relief deployment, and damage assessment. Social media data has the advantages such as real-time updates, diverse data types, and visual representation, but it also faces challenges such as limited quality and accuracy, excessive false information,limitations in user groups, and cultural differences. Harnessing the strengths of social media data while addressing the shortcomings of traditional monitoring methods is of paramount importance for urban emergency management departments in China to efficiently respond to flood disaster risks.
张扬, 陈轶. 基于社交媒体数据的洪水风险信息提取与应用研究综述[J]. 中国防汛抗旱, 2024, 34(2): 41-49.
ZHANG Yang, CHEN Yi. Review and application of flood risk information extraction based on social media data. journal1, 2024, 34(2): 41-49.
[1] Niles M T,Emery B F,Reagan A J,et al.Social media usage patterns during natural hazards[J].Plos One,2019,14(2):e210484. [2] Fohringer J,Dransch D,Kreibich H,et al.Social media as an information source for rapid flood inundation mapping[J]. Natural Hazards and Earth System Sciences,2015,15(12):2725-2738. [3] 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. [4] 王波,甄峰,孙鸿鹄.基于社交媒体签到数据的城市居民暴雨洪涝响应时空分析[J].地理科学,2020,40(9):1543-1552. [5] De Albuquerque J P,Herfort B,Brenning A,et al.A geographic approach for combining social media and authoritative data towards identifying useful information for disaster management[J]. International Journal of Geographical Information Science,2015,29(4):667-689. [6] Wang Z Y,Ye X Y.Social media analytics for natural disaster management[J]. International Journal of Geographical Information Science,2018,32(1):49-72. [7] Liu X,Guo H X,Lin Y,et al.Analyzing spatial-temporal distribution of natural hazards in China by mining news sources[J]. Natural Hazards Review,2018,19(3):4018006. [8] Mondal T,Pramanik P,Bhattacharya I,et al.Analysis and early detection of rumors in a post disaster scenario[J].Information Systems Frontiers,2018,20(5):961-979. [9] Gründer-Fahrer S,Schlaf A,Wiedemann G,et al.Topics and topical phases in German social media communication during a disaster[J].Natural Language Engineering,2018,24(2):221-264. [10] Yang J C,Yu M Z,Qin H,et al.A twitter data credibility framework-Hurricane Harvey as a use case[J].ISPRS International Journal of Geo-Information,2019,8(3):111. [11] de Bruijn J A,de Moel H,Jongman B,et al.A global database of historic and real-time flood events based on social media[J].Scientific data,2019,6(1):311. [12] Bai X S,Liu X X,Lu S H,et al.SEPM:Rapid seism emergency information processing based on social media[J]. Natural Hazards,2020,104:659-679. [13] Chaudhary P,D Aronco S,Leitao J P,et al. Water level prediction from social media images with a multi-task ranking approach[J].ISPRS Journal of Photogrammetry and Remote Sensing,2020,167:252-262. [14] Feng Y,Brenner C,Sester M. Flood severity mapping from volunteered geographic information by interpreting water level from images containing people:A case study of Hurricane Harvey[J].ISPRS Journal of Photogrammetry and Remote Sensing,2020,169:301-319. [15] Lopez-Fuentes L,Farasin A,Zaffaroni M,et al.Deep learning models for road passability detection during flood events using social media data[J].Applied Sciences,2020,10(24):8783. [16] Huang X,Wang C Z,Li Z L,et al.A visual-textual fused approach to automated tagging of flood-related tweets during a flood event[J].International Journal of Digital Earth,2019,12(11):1248-1264. [17] Wang R,Hu Y J,Zhou Z K,et al.Tracking flooding phase transitions and establishing a passive hotline with AI-enabled social media data[J].IEEE Access,2020,8:103395-103404. [18] Fan C,Jiang Y,Mostafavi A.Social sensing in disaster city digital twin:Integrated textual-visual-geo framework for situational awareness during built environment disruptions[J]. Journal of Management in Engineering,2020,36(3):4020002. [19] Michelsen N,Dirks H,Schulz S,et al.YouTube as a crowd-generated water level archive[J]. Science of the Total Environment,2016,568:189-195. [20] Jiang J C,Liu J Z,Cheng C X,et al.Automatic estimation of urban waterlogging depths from video images based on ubiquitous reference objects[J].Remote Sensing,2019,11(5):587. [21] Re M,Kazimierski L D,Garcia P E,et al.Assessment of crowdsourced social media data and numerical modelling as complementary tools for urban flood mitigation[J]. Hydrological Sciences Journal,2022,67(9):1295-1308. [22] Arthur R,Boulton C A,Shotton H,et al.Social sensing of floods in the UK[J].PloS one,2018,13(1):e189327. [23] Kankanamge N,Yigitcanlar T,Goonetilleke A,et al.Determining disaster severity through social media analysis:Testing the methodology with South East Queensland flood tweets[J].International Journal of Disaster Risk Reduction,2020,42:101360. [24] Sattaru J S,Bhatt C M,Saran S. Utilizing geo-social media as a proxy data for enhanced flood monitoring[J].Journal of the Indian Society of Remote Sensing,2021,49(9):2173-2186. [25] Fohringer J,Dransch D,Kreibich H,et al.Social media as an information source for rapid flood inundation mapping[J]. Natural Hazards and Earth System Sciences,2015,15(12):2725-2738. [26] Jongman B,Wagemaker J,Revilla Romero B,et al.Early flood detection for rapid humanitarian response:harnessing near real-time satellite and Twitter signals[J]. ISPRS International Journal of Geo-Information,2015,4(4):2246-2266. [27] Li J,He Z,Plaza J,et al.Social media:New perspectives to improve remote sensing for emergency response[J]. Proceedings of the IEEE,2017,105(10):1900-1912. [28] Huang X,Wang C Z,Li Z L.Reconstructing flood inundation probability by enhancing near real-time imagery with real-time gauges and tweets[J].IEEE Transactions on Geoscience and Remote Sensing,2018,56(8):4691-4701. [29] Wang H,Skau E,Krim H,et al.Fusing heterogeneous data:A case for remote sensing and social media[J].IEEE Transactions on Geoscience and Remote Sensing,2018,56(12):6956-6968. [30] Xu L,Ma A. Coarse-to-fine waterlogging probability assessment based on remote sensing image and social media data[J].Geo-spatial Information Science,2021,24(2):279-301. [31] Bruneau P,Brangbour E,Marchand-Maillet S,et al. Measuring the impact of natural hazards with citizen science:The case of flooded area estimation using Twitter[J].Remote Sensing,2021,13(6):1153. [32] Yang T F,Xie J B,Li G Q,et al.Extracting disaster-related location information through social media to assist remote sensing for disaster analysis:The case of the flood disaster in the Yangtze River Basin in China in 2020[J].Remote Sensing,2022,14(5):1199. [33] Lee C,Tien I. Probabilistic framework for integrating multiple data sources to estimate disaster and failure events and increase situational awareness[J]. ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems,Part A:Civil Engineering,2018,4(4):4018042. [34] Annis A,Nardi F. Integrating VGI and 2D hydraulic models into a data assimilation framework for real time flood forecasting and mapping[J]. Geo-spatial Information Science,2019,22(4):223-236. [35] Scotti V,Giannini M,Cioffi F.Enhanced flood mapping using synthetic aperture radar(SAR)images,hydraulic modelling,and social media:A case study of Hurricane Harvey(Houston,TX)[J].Journal of Flood Risk Management,2020,13(4):e12647. [36] Giler-Ormaza A,Carrivick J L,Smith M W.Using 2D-hydraulic modelling together with SfM and YouTube to estimate peak discharge[J].Tecnología y Ciencias del Agua,2021,12(3):348-378. [37] Stephenson J,Vaganay M,Coon D,et al. The role of Facebook and Twitter as organisational communication platforms in relation to flood events in Northern Ireland[J].Journal of Flood Risk Management,2018,11(3):339-350. [38] Wang R,Mao H N,Wang Y,et al.Hyper-resolution monitoring of urban flooding with social media and crowdsourcing data[J]. Computers&Geosciences,2018,111:139-147. [39] Baranowski D B,Flatau M K,Flatau P J,et al. Social-media and newspaper reports reveal large-scale meteorological drivers of floods on Sumatra[J].Nature Communications,2020,11(1):2503. [40] Restrepo-Estrada C,de Andrade S C,Abe N,et al.Geo-social media as a proxy for hydrometeorological data for streamflow estimation and to improve flood monitoring[J].Computers&Geosciences,2018,111:148-158. [41] Chen C C,Wang H.Using community information for natural disaster alerts[J].Journal of Information Science,2022,48(5):718-732. [42] Fang J,Hu J M,Shi X W, et al.Assessing disaster impacts and response using social media data in China:A case study of 2016 Wuhan rainstorm[J]. International Journal of Disaster Risk Reduction,2019,34:275-282. [43] Zhao Q S,Chen Z,Liu C,et al. Extracting and classifying typhoon disaster information based on volunteered geographic information from Chinese Sina microblog[J]. Concurrency and Computation:Practice and Experience,2019,31(9):e4910. [44] Arapostathis S G.A methodology for automatic acquisition of flood-event management information from social media:the flood in Messinia,South Greece,2016[J]. Information Systems Frontiers,2021,23(5):1127-1144. [45] Tyshchuk Y,Wallace W A.Modeling human behavior on social media in response to significant events[J].IEEE Transactions on Computational Social Systems,2018,5(2):444-457. [46] Cheng X X,Han G F,Zhao Y F,et al.Evaluating social media response to urban flood disaster:case study on an east asian city(Wuhan,China)[J].Sustainability,2019,11(19):5330. [47] Karmegam D,Mappillairaju B. Spatio-temporal distribution of negative emotions on Twitter during floods in Chennai,India,in2015:A post hoc analysis[J].International Journal of Health Geographics,2020,19(1):1-13. [48] Karami A,Shah V,Vaezi R,et al.Twitter speaks:A case of national disaster situational awareness[J].Journal of Information Science,2020,46(3):313-324. [49] Zhang C,Yao W L,Yang Y,et al.Semiautomated social media analytics for sensing societal impacts due to community disruptions during disasters[J].Computer-Aided Civil and Infrastructure Engineering,2020,35(12):1331-1348. [50] Geng S L,Zhou Q,Li M,et al.Spatial-temporal differences in disaster perception and response among new media users and the influence factors:A case study of the Shouguang Flood in Shandong Province[J].Natural Hazards,2021,105:2241-2262. [51] Cervone G,Sava E,Huang Q,et al.Using Twitter for tasking remotesensing data collection and damage assessment:2013 Boulder flood case study[J]. International Journal of Remote Sensing,2016,37(1):100-124. [52] Hao H Y,Wang Y.Leveraging multimodal social media data for rapid disaster damage assessment[J]. International Journal of Disaster Risk Reduction,2020,51:101760. [53] Liu X Y,Yang S N,Ye T,et al.A new approach to estimating floodaffected populations by combining mobility patterns with multisource data:A case study of Wuhan,China[J].International Journal of Disaster Risk Reduction,2021,55:102106. [54] Tan L,Schultz D M.Damage classification and recovery analysis of the Chongqing,China,floods of August 2020 based on social-media data[J].Journal of Cleaner Production,2021,313:127882. [55] Eckhardt D,Leiras A,ThoméA M T.Using social media for economic disaster evaluation:a systematic literature review and real case application[J].Natural Hazards Review,2022,23(1):5021020. [56] Schempp T,Zhang H,Schmidt A,et al.A framework to integrate social media and authoritative data for disaster relief detection and distribution optimization[J].International Journal of Disaster Risk Reduction,2019,39:101143. [57] Lin A Q,Wu H,Liang G H,et al.A big data-driven dynamic estimation model of relief supplies demand in urban flood disaster[J].International Journal of Disaster Risk Reduction,2020,49:101682. [58] Wu W J,Li J L,He Z Y,et al.Tracking spatio-temporal variation of geo-tagged topics with social media in China:A case study of 2016hefei rainstorm[J].International Journal of Disaster Risk Reduction,2020,50:101737. [59] Belcastro L,Marozzo F,Talia D,et al.Using social media for subevent detection during disasters[J]. Journal of Big Data,2021,8(1):1-22. [60] Chong W K,Naganathan H,Liu H,et al.Understanding infrastructure resiliency in Chennai,India using Twitter's Geotags and texts:a preliminary study[J].Engineering,2018,4(2):218-223. [61] Barker J L P,Macleod C J. Development of a national-scale realtime Twitter data mining pipeline for social geodata on the potential impacts of flooding on communities[J]. Environmental Modelling&Software,2019,115:213-227. [62] Wu Z N,Shen Y X,Wang H L,et al.Quantitative assessment of urban flood disaster vulnerability based on text data:case study in Zhengzhou[J].Water Supply,2020,20(2):408-415. [63] Karimiziarani M,Jafarzadegan K,Abbaszadeh P,et al. Hazard risk awareness and disaster management:Extracting the information content of twitter data[J].Sustainable Cities and Society,2022,77:103577. [64] Helmrich A M,Ruddell B L,Bessem K,et al.Opportunities for crowdsourcing in urban flood monitoring[J].Environmental modelling&software,2021,143:105124. [65] Koswatte S,Mcdougall K,Liu X.SDI and crowdsourced spatial information management automation for disaster management[J].Survey Review,2015,47(344):307-315.
2024, Vol. 34 
