Presentation	2013/7/15 Twitter User's Life Area Estimation Using Biased Topics Reflecting Area ,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	In this study, we propose Twitter user's life area estimation method using topics, by the assump-tion that the topics in the tweet appeared differently according to the area. Topics are created with LDA in each area by using the tweet sets from users who describe the area names in the Twitter's location field as training data. Then, we compare each topics, and grant regional label to the biased topic reflecting area. We implement classifiers to categorize tweets into the topics relevant to the area. Twitter user's life area is estimated based on the majority area labels in the topics assigned to the user's tweets. Through the user's life area estimation experiment by defining prefecture as area unit, and select 16 unit. The result was precision 0.59, recall 0.54, F-measure 0.56.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Twitter / Area estimation / Topic model
Paper #	Vol.2013-DBS-157 No.8,Vol.2013-IFAT-111 No.8
Date of Issue

Conference Information
Committee	DE
Conference Date	2013/7/15(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	Data Engineering (DE)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Twitter User's Life Area Estimation Using Biased Topics Reflecting Area
Sub Title (in English)
Keyword(1)	Twitter
Keyword(2)	Area estimation
Keyword(3)	Topic model
1st Author's Name
1st Author's Affiliation	()
Date	2013/7/15
Paper #	Vol.2013-DBS-157 No.8,Vol.2013-IFAT-111 No.8
Volume (vol)	vol.113
Number (no)	150
Page	pp.pp.-
#Pages	6
Date of Issue