Depression prevention support for workers based on pleasant / unpleasant stress prediction using emotion and mood.

2018 Fiscal Year Final Research Report

• Project/Area Number: 16K16471
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Rehabilitation science/Welfare engineering
• Research Institution: Komatsu University (2018); Ritsumeikan University (2016-2017)
• Principal Investigator: Yusuke Kajiwara 公立小松大学, 生産システム科学部, 准教授 (80710706)
• Project Period (FY): 2016-04-01 – 2019-03-31
• Keywords: ストレス / 感情 / 人工知能

Outline of Final Research Achievements

This study predicted emotions and moods from biosignals, behavior, and weather. Moreover, this study clarified predictors of emotions and moods. In addition, stressors were estimated with an accuracy of over 90% from biosignals. Furthermore, we proposed a method to estimate human mental state (pleasure / arousing / engagement) from the movement of the trunk during work, and verified the effect. In addition, we conducted an experiment in which the supervisor called for encouraging workers, and showed the effect. These results are useful for the psychological improvement of working environment. These results have already been published as papers, and 19 papers were accepted during the study period. Six of them are Science Citation Index Expanded registered papers.

Free Research Field

知覚情報処理

Academic Significance and Societal Importance of the Research Achievements

本研究では労働者の心理状態から各仕事が与える心理的ストレスを予測するため，労働者の心理状態を改善，悪化させる仕事を特定でき，うつ病の予防に適した，労働者の心理状態を望ましい方向に導く方策の実施を可能にする．またどんな仕事にも適用でき，実用性が高い．データベースに蓄積した情報は，平成27年12月から施行される労働安全衛生法の改正に伴うストレスチェックに用いることができ，事業者の負担増軽減と担当医師の診断支援に大いに貢献しうる．