Presentation 2023-09-07
A study on the emotional expression of virtual agents providing punishment and reward for behavior modification
Keishi Tainaka, Tatsuya Kobayashi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this study, we aim to modify the user's behavior by having a virtual agent (VA) punish and reward the user with a combination of emotions, such as anger and happiness. The VA can express emotions more richly than humans. However, the lack of a sufficient classification of these emotional expressions makes it challenging to design the VAs' actions. Therefore, we focus on animated characters, which are close to the VAs as virtual. We collected video scenes in which the animated characters communicate with each other and analyzed them based on their emotion and personality. Then, we discussed the emotional expressions of VAs for behavior modification.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) behavior modification / virtual agent / emotional expression / punishment / reward
Paper # MVE2023-18
Date of Issue 2023-08-31 (MVE)

Conference Information
Committee MVE
Conference Date 2023/9/7(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Kiyoshi Kiyokawa(NAIST)
Vice Chair Sumaru Niida(KDDI Research)
Secretary Sumaru Niida(Otsuma Women's Univ.)
Assistant Hidehiko Shishido(Univ. of Tsukuba) / Atsushi Nakazawa(Kyoto Univ.) / Naoya Tojo(KDDI Research) / Naoki Hagiyama(NTT) / Yuji Tatada(Univ. of Tokyo)

Paper Information
Registration To Technical Committee on Media Experience and Virtual Environment
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A study on the emotional expression of virtual agents providing punishment and reward for behavior modification
Sub Title (in English)
Keyword(1) behavior modification
Keyword(2) virtual agent
Keyword(3) emotional expression
Keyword(4) punishment
Keyword(5) reward
1st Author's Name Keishi Tainaka
1st Author's Affiliation KDDI Resarch, Inc.(KDDI Research)
2nd Author's Name Tatsuya Kobayashi
2nd Author's Affiliation KDDI Resarch, Inc.(KDDI Research)
Date 2023-09-07
Paper # MVE2023-18
Volume (vol) vol.123
Number (no) MVE-180
Page pp.pp.21-26(MVE),
#Pages 6
Date of Issue 2023-08-31 (MVE)