| 講演名 | 2022-02-21 User Satisfaction Prediction for Dialogue System in Mental Health Interventions 易 聖舟(東大), 菊地 俊暁(慶大), 山崎 俊彦(東大), |
|---|---|
| PDFダウンロードページ |  PDFダウンロードページへ |
| 抄録(和) | Mental health conditions deeply impact all areas of the life. Too much stress, most of which is related to work performance and interpersonal relationships, can lead to mental health disorders. Especially, under the influence of COVID-19, people have less chance to communicate with others, and it has become more difficult to get professional help face-to-face for improving mental health. Therefore, remote and automatic dialogue systems have been used for mental health interventions. The system can listen to people’s worries and help them relive stress. In order to provide appropriate support for different types of users’ worries, machine learning techniques were used to discover the topics and profound. In the end of using the dialogue system, the users were asked whether they are satisfied with the experience. According to the user satisfaction, we can maker clear which parts of the dialogue flow should be improved by using natural language models. They were used to simulate and continuously predict the user satisfaction. By observing how the predicted values change after the users answer each predetermined question, the inappropriate parts can be found because they tend to decrease the user satisfaction. Among the language models used in our experiments, BERT showed the highest validation accuracy of 76.04% for the user satisfaction prediction. |
| 抄録(英) | Mental health conditions deeply impact all areas of the life. Too much stress, most of which is related to work performance and interpersonal relationships, can lead to mental health disorders. Especially, under the influence of COVID-19, people have less chance to communicate with others, and it has become more difficult to get professional help face-to-face for improving mental health. Therefore, remote and automatic dialogue systems have been used for mental health interventions. The system can listen to people’s worries and help them relive stress. In order to provide appropriate support for different types of users’ worries, machine learning techniques were used to discover the topics and profound. In the end of using the dialogue system, the users were asked whether they are satisfied with the experience. According to the user satisfaction, we can maker clear which parts of the dialogue flow should be improved by using natural language models. They were used to simulate and continuously predict the user satisfaction. By observing how the predicted values change after the users answer each predetermined question, the inappropriate parts can be found because they tend to decrease the user satisfaction. Among the language models used in our experiments, BERT showed the highest validation accuracy of 76.04% for the user satisfaction prediction. |
| キーワード(和) | Mental Health / Dialogue System / Language Model / Topic Model |
| キーワード(英) | Mental Health / Dialogue System / Language Model / Topic Model |
| 資料番号 | ITS2021-25,IE2021-34 |
| 発行日 | 2022-02-14 (ITS, IE) |
| 研究会情報 | |
| 研究会 | IE / ITS / ITE-AIT / ITE-ME / ITE-MMS |
|---|---|
| 開催期間 | 2022/2/21(から2日開催) |
| 開催地（和） | オンライン開催 |
| 開催地（英） | Online |
| テーマ（和） | 画像処理，一般 |
| テーマ（英） | Image Processing, etc. |
| 委員長氏名（和） | 児玉 和也(NII) / 藤井 雅弘(宇都宮大) / 名手 久貴(東京工芸大) / 新井 啓之(日本工大) / 町田 賢司(NHK) |
| 委員長氏名（英） | Kazuya Kodama(NII) / Masahiro Fujii(Utsunomiya Univ.) / Hisaki Nate(Tokyo Polytechnic Univ.) / Hiroyuki Arai(Nippon Inst. of Tech.) / Kenji Machida(NHK) |
| 副委員長氏名（和） | 坂東 幸浩(NTT) / 山崎 俊彦(東大) / 大野 光平(明治大) / 橋本 尚久(産総研) / / 村松 正吾(新潟大) |
| 副委員長氏名（英） | Hiroyuki Bandoh(NTT) / Toshihiko Yamazaki(Univ. of Tokyo) / Kohei Ohno(Meiji Univ.) / Naohisa Hashimoto(AIST) / / Shogo Muramatsu(Niigata Univ.) |
| 幹事氏名（和） | 海野 恭平(KDDI総合研究所) / 福嶋 慶繁(名工大) / 橋浦 康一郎(秋田県立大) / 金 帝演(鶴岡工専) / / 望月 貴裕(NHK) / 小川 貴弘(北海道大) / 細井 利憲(NEC) / 山野 文子(コニカミノルタ) / 堀 淳志(三菱電機) / 文仙 正俊(福岡大) |
| 幹事氏名（英） | Kyohei Unno(KDDI Research) / Norishige Fukushima(Nagoya Inst. of Tech.) / Kouichiro Hashiura(Akita Prefectural Univ.) / Kim Jeyeon(NIT, Tsuruoka College) / / Takahiro Mochizuki(NHK) / Takahiro Ogawa(Hokkaido Univ.) / Toshinori Hosoi(NEC) / Ayako Yamano(KONICA MINOLTA) / Atsushi Hori(Mitsubishi Electric) / Masatoshi Bunsen(Fukuoka Univ.) |
| 幹事補佐氏名（和） | 岩村 俊輔(NHK) / 工藤 忍(NTT) / 今尾 勝崇(三菱電機) / 佐保 賢志(富山県立大) / 自見 圭司(群馬大) |
| 幹事補佐氏名（英） | Shunsuke Iwamura(NHK) / Shinobu Kudo(NTT) / Msataka Imao(Mitsubishi Electric) / Kenshi Saho(Toyama Prefectural Univ.) / Keiji Jimi(Gunma Univ.) |
| 講演論文情報詳細 | |
| 申込み研究会 | Technical Committee on Image Engineering / Technical Committee on Intelligent Transport Systems Technology / Technical Group on Artistic Image Technology / Technical Group on Media Engineering / Technical Group on Multi-media Storage |
|---|---|
| 本文の言語 | ENG |
| タイトル（和） | |
| サブタイトル（和） | |
| タイトル（英） | User Satisfaction Prediction for Dialogue System in Mental Health Interventions |
| サブタイトル（和） | |
| キーワード(1)（和/英） | Mental Health / Mental Health |
| キーワード(2)（和/英） | Dialogue System / Dialogue System |
| キーワード(3)（和/英） | Language Model / Language Model |
| キーワード(4)（和/英） | Topic Model / Topic Model |
| 第 1 著者 氏名（和/英） | 易 聖舟 / Shengzhou Yi |
| 第 1 著者 所属（和/英） | 東京大学(略称：東大) The University of Tokyo(略称：UTokyo) |
| 第 2 著者 氏名（和/英） | 菊地 俊暁 / Toshiaki Kikuchi |
| 第 2 著者 所属（和/英） | 慶應義塾大学(略称：慶大) Keio University(略称：Keio) |
| 第 3 著者 氏名（和/英） | 山崎 俊彦 / Toshihiko Yamasaki |
| 第 3 著者 所属（和/英） | 東京大学(略称：東大) The University of Tokyo(略称：UTokyo) |
| 発表年月日 | 2022-02-21 |
| 資料番号 | ITS2021-25,IE2021-34 |
| 巻番号（vol） | vol.121 |
| 号番号（no） | ITS-373,IE-374 |
| ページ範囲 | pp.1-6(ITS), pp.1-6(IE), |
| ページ数 | 6 |
| 発行日 | 2022-02-14 (ITS, IE) |