Presentation 2014-12-11
Detection of National and Local Events from Twitter
Yohei OGYU, Hisashi KOGA, Takahisa TODA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Event detection from Twitter has received a great amount of attention. Existing approaches are classified into the following two methods. One is to correct tweets by using keywords about events we determined in advance. The other is to correct tweets without supposing detected events or using keywords and analyze them for discovering what kinds of events are occurring. The latter method comprises two subcategories in terms of event types to be detected: news events spreading nationwide and that of local ones that happen in small-scale and limited area such as festivals and concert events. We attempted detection and classification by framework between national events and local events simultaneously by analyzing tweet's geographical variance. In previous work detecting those events simultaneously has not ever been addressed. We conducted an experiment with their data tweeted on November 2013 and discovered national events that cover a wide range of areas such as sports, news, anime, movie and local events that are remarkable ones.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Twitter / Event detection / Text mining / Natural language processing
Paper # PRMU2014-69
Date of Issue

Conference Information
Committee PRMU
Conference Date 2014/12/4(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Detection of National and Local Events from Twitter
Sub Title (in English)
Keyword(1) Twitter
Keyword(2) Event detection
Keyword(3) Text mining
Keyword(4) Natural language processing
1st Author's Name Yohei OGYU
1st Author's Affiliation Graduate School of Information Systems, The University of Electro-Communications()
2nd Author's Name Hisashi KOGA
2nd Author's Affiliation Graduate School of Information Systems, The University of Electro-Communications
3rd Author's Name Takahisa TODA
3rd Author's Affiliation Graduate School of Information Systems, The University of Electro-Communications
Date 2014-12-11
Paper # PRMU2014-69
Volume (vol) vol.114
Number (no) 356
Page pp.pp.-
#Pages 6
Date of Issue