Relationship between linguistic expression and human behavior for estimating crowd congestion degree after a large earthquake using Twitter data

2017 Fiscal Year Final Research Report

• Project/Area Number: 15K18176
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Town planning/Architectural planning
• Research Institution: Tokyo Institute of Technology
• Principal Investigator: Oki Takuya 東京工業大学, 環境・社会理工学院, 助教 (40712766)
• Project Period (FY): 2015-04-01 – 2018-03-31
• Keywords: 防災・減災 / 群集混雑度 / 混雑度評価点 / アドレスマッチング / Webアンケート / Twitter / 東日本大震災 / 時空間分布

Outline of Final Research Achievements

Using the tweets and photographs posted by users confronted with the crowd congestion, the possibility of grasping the degree of congestion in the facilities (such as railway stations), on the railway lines, or on the roads in real time was discussed.
More specifically, using tweets written in Japanese posted before and after the Great East Japan Earthquake (for 24 hours since 2:00 p.m. on March 11, 2011) as a case study, the method to extract tweets related to crowded conditions and the usefulness of tweets for grasping the time transition and spatial distribution of crowd congestion were demonstrated. Furthermore, conducting a Web questionnaire survey, the relationships between the actual congestion degree and the linguistic expressions about the congestion level and the selected behaviors were clarified.

Free Research Field

建築計画，都市防災