%0 Conference Proceedings
%T Visualization of Tweets and Related Images Posted During Disasters
%+ Research and Information Center [Tokyo] (TRIC)
%+ Department of Communication and Network Engineering
%+ Tokai University
%A Yamada, Sanetoshi
%A Utsu, Keisuke
%A Uchida, Osamu
%< avec comité de lecture
%( IFIP Advances in Information and Communication Technology
%B 5th International Conference on Information Technology in Disaster Risk Reduction (ITDRR)
%C Sofia, Bulgaria
%Y Yuko Murayama
%Y Dimiter Velev
%Y Plamena Zlateva
%I Springer International Publishing
%3 Information Technology in Disaster Risk Reduction
%V AICT-622
%P 26-35
%8 2020-12-03
%D 2020
%R 10.1007/978-3-030-81469-4_3
%K Disaster
%K Disaster mitigation
%K Twitter
%K Visualization
%K Co-occurrence network
%Z Computer Science [cs]Conference papers
%X To minimize damage during disasters, rapid collection and delivery of accurate information are essential. From this perspective, the use of social media, especially Twitter, in the case of a disaster has attracted worldwide attention. On the other hand, it is known that the number of tweets explodes at the time of a large-scale disaster. For example, at the time of the 2018 northern Osaka earthquake, more than 270,000 tweets containing the word “earthquake” were posted during the 10 min immediately after the quake. Therefore, it is essential to analyze the characteristics of tweets in order to make effective use of Twitter at the time of a disaster. In this study, we develop a system to simultaneously visualize the content of disaster-related tweets as well as the attached images that are related to their textual content. The purpose of constructing the system is to encourage prompt decision-making from local government and rapid evacuation actions by disaster-affected residents in the event of a disaster. From the visualization results using data from tweets posted during Typhoon Hagibis in 2019, it is shown that the proposed system is useful in the event of a disaster. It is also found that good results can be obtained by using datasets consisting of tweets posted during other disasters.
%G English
%Z TC 5
%Z WG 5.15
%2 https://inria.hal.science/hal-03761638/document
%2 https://inria.hal.science/hal-03761638/file/498235_1_En_3_Chapter.pdf
%L hal-03761638
%U https://inria.hal.science/hal-03761638
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-AICT
%~ IFIP-TC
%~ IFIP-TC5
%~ IFIP-WG
%~ IFIP-ITDRR
%~ IFIP-AICT-622
%~ IFIP-WG5-15