Construction of Learning Support AI Platform based on Prediction Model of Skill Forgetting

2022 Fiscal Year Final Research Report

• Project/Area Number: 21K18518
• Research Category: Grant-in-Aid for Challenging Research (Exploratory)
• Allocation Type: Multi-year Fund
• Review Section: Medium-sized Section 9:Education and related fields
• Research Institution: Future University-Hakodate
• Principal Investigator: Takegawa Yoshinari 公立はこだて未来大学, システム情報科学部, 教授 (60467678)
• Co-Investigator(Kenkyū-buntansha): 平田 圭二 公立はこだて未来大学, システム情報科学部, 教授 (30396121) ; 松原 正樹 筑波大学, 図書館情報メディア系, 准教授 (90714494)
• Project Period (FY): 2021-07-09 – 2023-03-31
• Keywords: 学習支援 / インタラクション / 情報デザイン / 機械学習

Outline of Final Research Achievements

The objective of this study is to categorize patterns of skill loss following skill gain, in order to develop a predictive model for skill retention in music games. The experiment was conducted using songs from the web-based music game ``Sparebeat.'' Participants were instructed to train daily on a piece of music slightly more challenging than their current skill level until they achieved a specified level of proficiency. Following this, participants took a break from training for at least one week, and their scores were recorded when they played the music immediately after the non-training phase. By analyzing the changes in scores during both the skill gain and loss phases, we identified three distinct patterns of skill loss.

Free Research Field

教育工学

Academic Significance and Societal Importance of the Research Achievements

HCI技術の進展により、テニスや楽器演奏などの技能習得を補助する学習支援システムが提案されている。既存システムとの比較では学習効率の向上が議論されているが、技能の衰退や忘却については考慮されていない。この研究では初心者の技能忘却モデルを構築し、脳科学や認知心理学、スポーツ科学への貢献を目指している。また、忘却を活用した学習支援システムや指導方法の検討にも応用が可能であり、教育現場への貢献も期待される。