Shaping Relatable Robots: A Child-Centered Approach to Social Personalization

Abstract

While social robots hold significant potential in education, not all children find their interaction with a robot relatable. We present a child-centered research approach that actively involves children in shaping personalized interaction content. We applied this method in a user study (n=102, 8-13 y.o) where we designed robot humor that was tailored to different age groups. Results indicated that children found age-personalized humor more amusing and felt a stronger affinity with it, both personally and at the group level. Our forthcoming longitudinal study will focus on enhancing children's relatedness to the robot and a book, aiming to stimulate reading motivation. We plan to investigate how generative AI can efficiently scale up both co-design and content creation steps.