自然災害和人為災害包括交通事故，火災和地震等，都可能導致嚴重的財產損失和經濟損失，因此，災難管理機制之運作及面對緊急事件時之反應速度無疑是很重要的，而其中最難的任務之一，就是迅速準確地掌握災害事件發生當下的最新狀況。有鑑於此，我們發現當災害事件發生時，現場目擊的民眾會藉由社群媒體發送即時訊息，以迅速聯繫親朋好友並分享相關資訊與影音圖片等，這樣的訊息傳播往往比傳統媒體發佈新聞更快速。明確地而言，社群媒體正憑藉著其即時性、巨大的數據規模和全球人口龐大的使用量，遠遠優於常規的傳統媒體。在本研究中，我們提出了一個監測災害事件的輔助系統，透過收集與分析社群媒體中的文章，以即時地監控是否有災難事件發生，而藉助資料視覺化技術，社群媒體上的第一手資料，可以幫助災難緊急應變中心更快速地了解情況，經由實驗探討，本研究所提出之系統在多個實際事件中能真正幫助後續災難管理機制的順利運行。

Disasters and emergencies including traffic accidents, fire and earthquakes can cause property damage loss of lives and economic damages. Nevertheless, one of the most difficult tasks for agencies in disaster management is to rapidly and accurately identify the latest status of a disaster event. In view of this, it is noted that witnesses of a disaster event send instant messages on the social media so as to contact their families and friends, post photos and share stories. Such a way is usually much faster than the news reporting on conventional media. Specifically, social media has played an important role in spreading information of disaster events by enabling people to share and ask for help. In this work, we thus propose an online supporting scheme to monitor and track disaster events. Invaluable clues embedded in huge amounts of online messages can be discovered with an appropriately supporting scheme when carefully exploiting the information over content, temporal, and social dimensions. Specifically, multiple data sources are crawled from social networks to conduct real-time analysis and to present interactive visualization. Experimental studies show that the proposed scheme is feasible for agencies in practical usage.

[1] S. Choi, “The Analysis Technique Of Social Media For Disaster Management,” Proceedings of International Journal of Design and Nature and Ecodynamics, 2016.
[2] A. Marcus, M.S. Bernstein, O. Badar, D.R. Karger, S. Madden and R.C. Miller, “Twitinfo: aggregating and visualizing microblogs for event exploration,” Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, 2011.
[3] S. Mazumdar, V. Lanfranchi, N. Ireson and F. Ciravegna, “Visual Analysis of Real-time Social Media for Emergency Response” Proceedings of the ESWC Conference, 2014.
[4] E. Alexander, “Social Media in Disaster Risk Reduction and Crisis Management,” Proceedings of Journal of Science and Engineering Ethics, 2014.
[5] M. Latonero, “Emergency Management, Twitter,and Social Media Evangelism,” Proceedings of International Journal of Information Systems for Crisis Response and Management, 2011.
[6] A. Nurwidyantoro, E. Winarko, “Event Detection in Social Media: a Survey,” Proceedings of International Conference on ICT for Smart Society, 2013.
[7] G. Valkanas, D. Gunopulos, “Event Detection from Social Media Data,” IEEE Transactions on Computer Society Technical Committee on Data Engineering, 2013.
[8] T. Baldwin, P. Cook, B. Han, A. Harwood, S. Karunasekera and M. Moshtaghi, “A Support Platform for Event Detection using Social Intelligence,” Proceedings of the Conference on Computational Linguistics, 2012.
[9] V. Pekar, J. Binner, H. Najafi “Detecting Mass Emergency Events on Social Media: One Classification Problem or Many,” Proceedings of International Conference on Data Mining, 2016.
[10] M. Moss, A. Townsend, “Disaster Forensics: Leveraging Crisis Information Systems for Social Science,” Proceedings of the International ISCRAM Conference, 2006.
[11] C. Wang, Q. Wang, K. Ren “Privacy-Preserving Public Auditing for Data Storage Security in Cloud Computing,” Proceedings of IEEE INFOCOM, 2010.
[12] D. Yates, S. Paquette, “Emergency knowledge management and social media technologies: A case study of the 2010 Haitian earthquake,” Proceedings of International Journal on Information Management, 2011.
[13] Q. Zhao, P. Mitra, “Event Detection and Visualization for Social Text Streams,” Proceedings of the Conference on ICWSM, 2007.
[14] W. Dou, X. Wang, W. Ribarsky and M. Zhou, “Event Detection in Social Media Data,” University of North Carolina at Charlotte, IBM Almaden Research Center, 2012.
[15] H. Gao, G. Barbier and R. Goolsby, “Harnessing the Crowdsourcing Power of Social Media for Disaster Relief,” IEEE Journal on Intelligent Systems, 2011.
[16] K. Starbird, L. Palen, “Pass It On?: Retweeting in Mass Emergency,” Proceedings of International Conference on ISCRAM, 2010.
[17] M.A. Sutton1, S. Reis, G. Billen, P. Cellier, J.W. Erisman, A.R. Mosier, E. Nemitz, J. Sprent, H. Grinsven, M. Voss, C. Beier, and U. Skiba, “Nitrogen & Global Change,” Published by Copernicus Publications on behalf of the European Geosciences Union, 2008.
[18] A.L. Hughes, L. Palen, “Twitter Adoption and Use in Mass Convergence and Emergency Events,” Proceedings of International Conference on ISCRAM, 2009.
[19] K. Starbird, J. Stamberger, “Tweak the Tweet: Leveraging Microblogging Proliferation with a Prescriptive Syntax to Support Citizen Reporting,” Proceedings of International Conference on ISCRAM, 2010.
[20] P. Dewan, M. Gupta, K. Goyal, P. Kumaraguru, “MultiOSN: Realtime Monitoring of Real World Events on Multiple Online Social Media,” Proceedings of IBM Collaborative Academia Research Exchange Workshop, 2013.
[21] R. Li, K.H. Lei, R. Khadiwala, K. Chen, “TEDAS: A Twitter-based Event Detection and Analysis System,” Proceedings of IEEE International Conference on Data Engineering, 2012.
[22] A. Farahat, F. Chen, and T. Brants, “Optimizing story link detection is not equivalent to optimizing new event detection,” Proceedings of the 41st Annual Meeting on Association for Computational Linguistics, 2003.
[23] M. Imran, C. Castillo, F. Diaz, S. Vieweg, “Processing Social Media Messages in Mass Emergency: A Survey,” Proceedings of Journal on ACM Computing Surveys, 2015.
[24] A.L. Hughes, L. Palen, “Twitter adoption and use in mass convergence and emergency events,” Proceedings of Journal on Emergency Management, 2009.
[25] SAS Institute Inc., “History of Data Visualization", 2017, [online] Available: https://www.sas.com/en_us/insights/big-data/data-visualization.html.