Presentation 2019-10-26
Predicting Personality based on Ad-Request Logs
Akihiro Kobayashi, Yuichi Ishikawa, Shigeru Kuroyanagi, Atsunori Minamikawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently role of customers’ personality traits is one of the main topics in advertising technologies. Predicting personality traits of customers who visit a web page displaying banner ads without questionnaire will profit advertising distributor. However, conventional methods are limited to users who post texts or images on SNS. We extract behavioral characteristics of users' browsing on the WWW from the ad-request log based on embedding techniques used in natural language processing and predict personality traits of the users from the characteristics. We verified accuracy of the estimator (MAX ROC-AUC=0.612) by cross-validation.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Personality / Web behavior analytics / word2vec
Paper # HCS2019-40
Date of Issue 2019-10-19 (HCS)

Conference Information
Committee HCS
Conference Date 2019/10/26(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Nihon Univ.
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Masafumi Matsuda(NTT)
Vice Chair Tomoo Inoue(Univ. of Tsukuba) / Yugo Hayashi(Ritsumeikan Univ.)
Secretary Tomoo Inoue(Kanazawa Inst. of Tech.) / Yugo Hayashi(Osaka Electro-Comm. Univ.)
Assistant Tomoko Kanda(Osaka Inst. of Tech.) / Kazuki Takashima(Tohoku Univ.) / Ken Fujiwara(Osaka Univ. of Economic) / Kazunori Terada(Gifu Univ.) / Atsushi Kimura(Nihon Univ.) / HUANG HUNGHSUAN(Riken)

Paper Information
Registration To Technical Committee on Human Communication Science
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Predicting Personality based on Ad-Request Logs
Sub Title (in English)
Keyword(1) Personality
Keyword(2) Web behavior analytics
Keyword(3) word2vec
1st Author's Name Akihiro Kobayashi
1st Author's Affiliation KDDI Research Inc.(KDDI Research Inc.)
2nd Author's Name Yuichi Ishikawa
2nd Author's Affiliation KDDI Research Inc.(KDDI Research Inc.)
3rd Author's Name Shigeru Kuroyanagi
3rd Author's Affiliation Supership Inc.(Supership)
4th Author's Name Atsunori Minamikawa
4th Author's Affiliation KDDI Research Inc.(KDDI Research Inc.)
Date 2019-10-26
Paper # HCS2019-40
Volume (vol) vol.119
Number (no) HCS-252
Page pp.pp.1-6(HCS),
#Pages 6
Date of Issue 2019-10-19 (HCS)