Presentation | 2012-12-19 Twitter User's Residence Estimation Using Multi-class Classification with Area-specific Term Selection Hayato Nishimura, Yoshihiko Suhara, Seiji Susaki, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, we propose area-specific term selection method based on users' residential information described in their profile and the users' tweets.Our method extracts bag-of-words from a user's tweet and regards the residence as a label to predict a user's residence in the multiclass classification framework.We conducted experiments on Japanese Twitter dataset, and we confirmed that our proposed method outperforms baseline method in terms of accuracy. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | MicroBlog / Twitter / Location Estimation |
Paper # | NLC2012-37 |
Date of Issue |
Conference Information | |
Committee | NLC |
---|---|
Conference Date | 2012/12/12(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 | Natural Language Understanding and Models of Communication (NLC) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Twitter User's Residence Estimation Using Multi-class Classification with Area-specific Term Selection |
Sub Title (in English) | |
Keyword(1) | MicroBlog |
Keyword(2) | |
Keyword(3) | Location Estimation |
1st Author's Name | Hayato Nishimura |
1st Author's Affiliation | Nara Institute of Science and Technology() |
2nd Author's Name | Yoshihiko Suhara |
2nd Author's Affiliation | NTT Service Evolution Laboratories, NTT Corporation |
3rd Author's Name | Seiji Susaki |
3rd Author's Affiliation | NTT Service Evolution Laboratories, NTT Corporation |
Date | 2012-12-19 |
Paper # | NLC2012-37 |
Volume (vol) | vol.112 |
Number (no) | 367 |
Page | pp.pp.- |
#Pages | 5 |
Date of Issue |