Development of a Society 5.0-oriented problem-solving learning evaluation index and feedback system

2022 Fiscal Year Final Research Report

• Project/Area Number: 19K12246
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 62020:Web informatics and service informatics-related
• Research Institution: Gifu National College of Technology
• Principal Investigator: Ogawa Nobuyuki 岐阜工業高等専門学校, その他部局等, 教授 (60270261)
• Co-Investigator(Kenkyū-buntansha): 兼松 秀行 鈴鹿工業高等専門学校, その他部局等, 特命教授 (10185952) ; 矢島 邦昭 仙台高等専門学校, 総合工学科, 教授 (90259804) ; 中平 勝子 長岡技術科学大学, 工学研究科, 准教授 (80339621)
• Project Period (FY): 2019-04-01 – 2023-03-31
• Keywords: 教育サービス / Society 5.0 / 問題解決型学習評価指標 / フィードバックシステム / PBL

Outline of Final Research Achievements

In this study, we developed an evaluation index for objectively estimating and analyzing the activity level in a learning situation as a new evaluation method for discussion-based learning. We practiced the effectiveness of implementing a feedback system in educational activities. We have practiced more objective evaluation by analyzing the situation of the learning place, such as the analysis of questionnaire responses written subjectively by learners, the contents of learners' reports, and discourse analysis of recorded conversations, and by measuring brain activity level as an additional measure by taking a composite of speech information (phoneme analysis), eye movement, and gaze measurement, which can be acquired based on biometric data. The results were evaluated more objectively. The results apply to groups sharing a physical space and PBL conducted by teleconferencing systems (e.g., Metaverse, videoconferencing systems, etc.).

Free Research Field

教育工学，教育サービス

Academic Significance and Societal Importance of the Research Achievements

本研究では，教育サービスにSociety 5.0を取り入れ，物理空間を共有しない新しい議論型学習の評価法として学習の場における活性度を客観的に推定・分析するための評価指標を開発し，教育活動におけるフィードバックシステムの有効性を実践した．議論型学習は，アクティブラーニングの中でも最も効果的とされる問題解決型学習（PBL）を対象とし，学習の場の活性度を推定し，学習の場へフィードバック，学習の場の活性度推定に必要な情報の策定と，時刻同期を工夫した集約方法の開発，収集されるマルチモーダル生体情報と，学習者の心的状態の関係を機械学習の手法を用いてパタン化し，場の活性度推定を可能とすることができた．