OPEN ACCESS
Social media has transformed mass media based information traffic, and it has become a key resource for finding value in enterprises and public institutions. Particularly, with regard to disaster management, the necessity for public participation in policy development through the use of social media is emphasized. National Disaster Management Research Institute developed the Social Big Board, which is a system that monitors social Big Data in real time for the purpose of implementing social media disaster management. This real time monitoring system provides various information and insights based on the tweets, such as disaster issues, tweet frequency by region, original tweets, etc. The purpose of using this system is to take advantage of the potential benefits of social media in relation to disaster management. In this paper, Korean language text mining based Social Big Board will be briefly introduced, and disaster issue detection model, which is the key algorithms, will be described. The detection model of potential issues of these key algorithms is intensively defined and the performance of the models are compared and evaluated.
big data, disaster issue detection, disaster management, social media
[1] Choi, S.H., The model for sensing of disaster signs based on big data. Journal of Korean Society of Hazard Mitigation, 14(2), pp. 149–157, 2014 (In Korean). http://dx.doi.org/10.9798/KOSHAM.2014.14.2.149
[2] Choi, S.H., The model for sensing of disaster signs based on big data. Proceeding of the International Conference on CAIPT, pp. 169–172, 2013.
[3] Seon, H.C. & Byung, G.B., Disaster issue detection model from social big data. Information Science Society Journal, 20(5), pp. 286–290, 2014 (In Korean).
[4] Jeannette, S., Leysia, P. & Irina, S., Backchannels on the front lines: emergent uses of social media in the 2007 Southern California Wildfires. Proceedings of the 5th International ISCRAM Conference, Washington DC., USA, 2008.
[5] Seon, H.C., Jong, G.L. & Woon, G.Y., Disaster management competnece reinforcement for self-governing bodies using big data. Local Administration, 730, pp. 16–19, 2014 (In Korean).
[6] Tsolmon, B., Kwon, A.R. & Lee, K.S., Extracting social events based on timeline and sentiment analysis in twitter corpus. Natural Language Processing and Information Systems LNCS, 7337, pp. 265–270, 2012.
http://dx.doi.org/10.1007/978-3-642-31178-9_32
[7] Seon, H.C., Disaster issue detection model from disaster relevance rate based social big data. Academic Conference Journal of Korea Information Processing Society, pp. 829–832, 2014 (In Korean).
[8] The Urban Geographies of Hurricane Sandy in New York City, floating sheep, available at http://www.floatingsheep.org/2012/10/the-urban-geographies-of-hurricane.html
[9] Hurricane Sandy and the Geographies of Flooding on Twitter, floating sheep, available at http://www.floatingsheep.org/2012/10/hurricane-sandy-and-geographies-of.html