Presentation 2019-02-07
Finding Reliable Rescue Request in Disasters
Chenjie Song, Hiroyuki Fujishiro,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A large amount of unverified information circulating on social media has prevented it from being efficiently utilized for relief efforts in the event of natural disasters. We analyzed and revealed particular features of such tweets, based on a dataset of tweets that had actually led to saving lives of people affected by the 2018 west Japan heavy rain disaster, provided and confirmed by Japan Broadcasting Corporation (NHK). We then compared the features to another set of tweets in an attempt to differentiate ones that includes crucial information related to rescue requests. As a result, 71 percent of the tweets we collected based on the features were reliable rescue requests.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) social media / Twitter / disaster information / rescue request
Paper # NLC2018-36
Date of Issue 2019-01-31 (NLC)

Conference Information
Committee NLC / IPSJ-IFAT
Conference Date 2019/2/7(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Ryukoku University Omiya Campus
Topics (in Japanese) (See Japanese page)
Topics (in English) The 14th Text Analytics Symposium
Chair Takeshi Sakaki(Hottolink)
Vice Chair Mitsuo Yoshida(Toyohashi Univ. of Tech.) / Kazutaka Shimada(Kyushu Inst. of Tech.)
Secretary Mitsuo Yoshida(Ryukoku Univ.) / Kazutaka Shimada(NTT)
Assistant Takeshi Kobayakawa(NHK) / Hiroki Sakaji(Univ. of Tokyo)

Paper Information
Registration To Technical Committee on Natural Language Understanding and Models of Communication / Special Interest Group on Information Fundamentals and Access Technologies
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Finding Reliable Rescue Request in Disasters
Sub Title (in English) Analysis of " Rescue" Tweet in 2018 West Japan Heavy Rain Disaster
Keyword(1) social media
Keyword(2) Twitter
Keyword(3) disaster information
Keyword(4) rescue request
1st Author's Name Chenjie Song
1st Author's Affiliation Hosei University(Hosei Univ.)
2nd Author's Name Hiroyuki Fujishiro
2nd Author's Affiliation Hosei University(Hosei Univ.)
Date 2019-02-07
Paper # NLC2018-36
Volume (vol) vol.118
Number (no) NLC-439
Page pp.pp.7-12(NLC),
#Pages 6
Date of Issue 2019-01-31 (NLC)