JSAI2022

Presentation information

Organized Session

Organized Session » OS-12

[3H3-OS-12a] グループインタラクションとAI(1/2)

Thu. Jun 16, 2022 1:30 PM - 3:10 PM Room H (Room H)

オーガナイザ:酒造 正樹(東京電機大学)[現地]、湯浅 将英(湘南工科大学)、岡田 将吾(北陸先端科学技術大学院大学)、酒井 元気(日本大学)、近藤 一晃(京都大学)、中野 有紀子(成蹊大学)

1:50 PM - 2:10 PM

[3H3-OS-12a-02] A Multiparty Model for Estimating Persuasiveness in Group Discussions

〇Atsushi Ito1, Tatsuya Sakato1, Yukiko Nakano1, Fumio Nihei2, Ryo Ishii2, Atsushi Fukayama2, Takao Nakamura2 (1. Seikei University, 2. NTT Human Informatics Laboratories)

[[Online]]

Keywords:persuasiveness, Group Discussion, Multi-party deep learning

Persuasiveness is an important communication skill in communicating with others. This study aims to estimate the persuasiveness of the participants in group discussions. First, human annotators rated the level of persuasiveness of each of four participants in group discussions. Next, GRU-based neural networks were used to create speech, verbal, and visual (head pose) encoders. The output from each encoder was combined to create a multimodal and multiparty model to estimate the persuasiveness of each participant. The experiment results showed that multimodal and multiparty models are better than unimodal and single-person models. The best performing multimodal multiparty model achieved 80% accuracy in predicting high/low persuasiveness, and 77% accuracy in predicting the most persuasive participant in the group.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.

Password