2026-03-30シカゴ大学
A new study from the University of Chicago shows children can learn about empathy, conflict and problem-solving from robot tutors—but it’s actually best if the robots don’t pretend to be human.Photo by Stephen Garrett
＜関連情報＞
- https://news.uchicago.edu/story/teach-social-emotional-skills-does-robot-need-pretend-be-human
- https://dl.acm.org/doi/10.1145/3757279.3785596
- https://hri.cs.uchicago.edu/publications/HRI_2026_Wright_Fictional_vs_Factual.pdf
架空のロボット家庭教師の対話と事実に基づいた対話は、子どもの社会情緒的学習に影響を与える可能性がある Fictional vs. Factual Robot Tutor Dialogue Can Shape Child Social-Emotional Learning
Lauren L. Wright, Kaitlyn Li, Hewitt Watkins, Kiljoong Kim, Sarah Sebo
HRI ’26: Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction Published: 16 March 2026
DOI:https://doi.org/10.1145/3757279.3785596
Abstract
Social-emotional learning (SEL) is an educational framework that helps children develop the skills necessary for academic and life success. However limited resources restrict most schools to whole-group SEL instruction which may not benefit all students. In this work, we explore using social robots to address this challenge and how a robot’s dialogue style can influence the effectiveness of one-on-one SEL lessons. The dialogue styles we investigate are (1) fictional dialogue, where the robot is human-like with emotions and discusses SEL scenarios as first person anecdotes, and (2) factual dialogue, where the robot is transparent, lacks emotions, and discusses scenarios from the third person. In a between-subjects study (N=52) at Chicago schools, students aged 9-10 were either part of a control group, receiving no robot instruction, or received four SEL lessons across two weeks from either the fictional or factual robot. We found that students who had lessons with either robot improved more in lesson skill than students in the control. We also found that during lessons students spoke to the factual robot using more lesson concepts than those talking to the fictional robot, indicating that first person storytelling and emotional disclosure from a robot may be unnecessary for, or even hinder, SEL learning with a robot.
