Open AccessGrasp of Disaster Situation and Support Need Inside Affected Area with Social Sensing – An Analysis of Twitter Data Before and After the 2011 Great East Japan Earthquake Disaster Occurring –
Author(s) -
Shosuke Sato,
Kazumasa Hanaoka,
Makoto Okumura,
Shunichi Koshimura
Publication year - 2016
Publication title -
journal of disaster research
Language(s) - English
Resource type - Journals
eISSN - 1883-8030
pISSN - 1881-2473
DOI - 10.20965/jdr.2016.p0198
Subject(s) - natural disaster , social media , disaster area , computer science , emergency management , data science , grasp , geography , computer security , world wide web , meteorology , political science , law , programming language
There are increasing expectations that social sensing, especially the analysis of social media text as a source of information for COP (Common Operational Picture), is useful for decision-making about responses to disasters. This paper reports on a geo-information and content analysis of three million Twitter texts sampled from Japanese Twitter accounts for one month before and after the 2011 Great East Japan Earthquake disaster. The results are as follows. 1) The number of Twitter texts that include geotag (latitude and longitude information) is too small for reliable analysis. However, a method of detecting the tweet’s location from the tweet’s text using GeoNLP (an automatic technology to tag geo-information from natural language text) is able to identify geo-information, and we have confirmed that many tweets were sent from stricken areas. 2) A comparison of Twitter data distribution before and after the disaster occurred does not identify clearly which areas were significantly affected by the disaster. 3) There were very few Twitter texts that included information about the damage in affected areas and their support needs.