Teachable agent for improving Ikigai

• Main Author: Chen, Ping
• Other Authors: Miao Chun Yan
• Format: Thesis-Doctor of Philosophy
• Language: English
• Published: Nanyang Technological University 2024
• Subjects: Computer and Information Science; Teachable agent; Ikigai; Geriatric care
• Online Access: https://hdl.handle.net/10356/175775
• Institution: Nanyang Technological University

The global elderly population is projected to more than double by 2050, emphasizing the need for meaningful elderly care. We delved into “Ikigai”, a concept that originated in Japan, signifying an individual’s purpose and satisfaction in life. In this research, we aim to assess and enhance an individual’s Ikigai level. We introduce a knowledge graph-based survey system for dynamic Ikigai assessments, improving response reliability and reflecting Ikigai’s evolving essence. Additionally, we propose a supervised learning model that predicts Ikigai levels from user profiles to help continuous evaluation. For Ikigai enhancement, we propose a teachable agent for the elderly, aiming to stimulate cognitive abilities and heighten self-esteem. Additionally, a reinforcement learning-driven hobby recommender recommends potential Ikigai-boosting activities based on personal attributes. Through a phenomenographic analysis, we explore individual perceptions of these methods, revealing how technology can bolster life’s purpose and meaning. Our pioneering research uniquely fuses advanced techniques with Ikigai exploration.