Presentation 2017-07-21
Author Profiling
Bouazizi Mondher, Beylerian Anthony, Watanabe Hajime, Ohtsuki Tomoaki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Author profiling refers to the process of automatically detecting characteristic of a given author such as his gender, age range or personality from his own data. This is mainly useful in fields such as advertising and marketing where reviewers of products for example are grouped based on such characteristics even if they are anonymous. In this paper, we propose new sets of features, aimed at short text samples written by the same author, for both gender and age range detection. The feature sets are mainly composed of both probabilistic features as well as writing patterns, which can be automatically extracted from the texts of the author. We evaluate the performance of these features using the Machine Learning algorithm ``Random Forest'' classifier and a dataset based on different authors’Twitter feeds. In our experiments, the proposed approach reaches a detection accuracy of up to 83% for gender and 73% for age range.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Twitter / Author Profiling / Machine Learning
Paper # ASN2017-60
Date of Issue 2017-07-12 (ASN)

Conference Information
Committee NS / ASN / RCC / RCS / SR
Conference Date 2017/7/19(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Hokkaido Univ.
Topics (in Japanese) (See Japanese page)
Topics (in English) Wireless Distributed Network, M2M (Machine-to-Machine), D2D (Device-to-Device),etc.
Chair Hideki Tode(Osaka Pref. Univ.) / Hiraku Okada(Nagoya Univ.) / Shinsuke Hara(Osaka City Univ.) / Hidekazu Murata(Kyoto Univ.) / Kenta Umebayashi(Tokyo Univ. of Agric. and Tech.)
Vice Chair Yoshikatsu Okazaki(NTT) / Shigeki Shiokawa(KAIT) / Jin Nakazawa(Keio Univ.) / Satoru Yamano(NEC) / Kazunori Hayashi(Osaka City Univ.) / Ryu Miura(NICT) / Yukitoshi Sanada(Keio Univ.) / Eisuke Fukuda(Fujitsu Labs.) / Satoshi Suyama(NTT DoCoMo) / Masayuki Ariyoshi(NEC) / Suguru Kameda(Tohoku Univ.)
Secretary Yoshikatsu Okazaki(Kyushu Inst. of Tech.) / Shigeki Shiokawa(NTT) / Jin Nakazawa(NICT) / Satoru Yamano(Sophia Univ.) / Kazunori Hayashi(Kagawa Univ.) / Ryu Miura(Hokkaido Univ.) / Yukitoshi Sanada(Toshiba) / Eisuke Fukuda(Hokkaido Univ.) / Satoshi Suyama(NICT) / Masayuki Ariyoshi(ATR) / Suguru Kameda
Assistant Kenichi Kashibuchi(NTT) / Hiroto Aida(Doshisha Univ.) / Tomoyuki Ota(Hiroshima City Univ.) / Tatsuya Kikuzuki(Fujitu Lab.) / Ryo Nakano(HITACHI) / Yoshifumi Hotta(Mitsubishi Electric) / Toshinori Kagawa(NICT) / Kentaro Kobayashi(Nagoya Univ.) / Tetsuya Yamamoto(Panasonic) / Koichi Ishihara(NTT) / Kazushi Muraoka(NEC) / Shinsuke Ibi(Osaka Univ.) / Hiroshi Nishimoto(Mitsubishi Electric) / Mamiko Inamori(Tokai Univ.) / Hiroyuki Shiba(NTT) / Gia Khanh Tran(Tokyo Inst. of Tech.) / Syusuke Narieda(NIT, Akashi College)

Paper Information
Registration To Technical Committee on Network Systems / Technical Committee on Ambient intelligence and Sensor Networks / Technical Committee on Reliable Communication and Control / Technical Committee on Radio Communication Systems / Technical Committee on Smart Radio
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Author Profiling
Sub Title (in English) Gender and Age Detection from Short Texts
Keyword(1) Twitter
Keyword(2) Author Profiling
Keyword(3) Machine Learning
1st Author's Name Bouazizi Mondher
1st Author's Affiliation Keio University(Keio Univ.)
2nd Author's Name Beylerian Anthony
2nd Author's Affiliation Keio University(Keio Univ.)
3rd Author's Name Watanabe Hajime
3rd Author's Affiliation Keio University(Keio Univ.)
4th Author's Name Ohtsuki Tomoaki
4th Author's Affiliation Keio University(Keio Univ.)
Date 2017-07-21
Paper # ASN2017-60
Volume (vol) vol.117
Number (no) ASN-134
Page pp.pp.241-246(ASN),
#Pages 6
Date of Issue 2017-07-12 (ASN)