A Study on Embodied Expression based on Body Movement - Emotion Bigdata and Its Application for Machine Learning

2022 Fiscal Year Final Research Report

• Project/Area Number: 20H04096
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Review Section: Basic Section 59030:Physical education, and physical and health education-related
• Research Institution: Kwansei Gakuin University
• Principal Investigator: Yamamoto Michiya 関西学院大学, 工学部, 教授 (60347606)
• Co-Investigator(Kenkyū-buntansha): 青柳 西蔵 駒澤大学, グローバル・メディア・スタディーズ学部, 講師 (20646228) ; 長松 隆 神戸大学, 海事科学研究科, 教授 (80314251) ; 廣江 葵 関西学院大学, 工学部, 研究員 (40963228) ; 阪田 真己子 同志社大学, 文化情報学部, 教授 (10352551)
• Project Period (FY): 2020-04-01 – 2023-03-31
• Keywords: 身体動作表情 / ラバン行動分析

Outline of Final Research Achievements

Technologies for sensing and understanding human body movements has been developed. By focusing on the generality of Laban Movement Analysis, we constructed a embodied movement bigdata, developed original feature values, and estimation of internal states such as emotions. In this study, we performed a study on embodied expression for comprehensive understanding of them and its application for machine learning. In detail, we constructed big data of a video watching task with small body and a vispoke task with various movements, developed new feature values and their evaluation using machine learning. We thus clarified what is embodied expressions, such as the direction of body movement which express more about internal state.

Free Research Field

ヒューマンインタフェース

Academic Significance and Societal Importance of the Research Achievements

身体表現理論を起点とする本研究は、普遍性の高さ、実証研究との近さという点で、他の感情認識研究と一線を画する。精緻な身体動作‐感情ビッグデータを活用して、身体を介した感情表出における性質「身体動作表情」が明らかにされた例はなく、この知見を機械学習に応用し、その活用基盤を構築することは、将来の、人と情報環境のかかわりの在り方を大きく変容させるものである。