Design and Evaluation of a Photorealistic AI Virtual Peer in Elementary Collaborative Classroom

要旨

In elementary education, students struggle to articulate uncertainties, limiting diverse perspectives in classroom discussions, particularly in small schools where limited participants constrain collaborative learning. This study designed and evaluated ``Saya,'' a photorealistic AI virtual peer functioning as an additional student. We implemented five teacher-controlled speech acts (expand, probe, summarize, lighten, and incorrect answer) through dynamic classroom dialogue generation using GPT-4o-mini. Field studies in Japanese elementary schools (large class: 27 students, small class: 2 students) demonstrated that Saya integration increased the proportion of student speaking time by 1.28 times and 2.07 times respectively, with 95.6% and 100% of students expressing desire for future Saya-integrated lessons. Teachers reported enhanced student concentration and listening behaviors, noting that interactions with Saya prompted students to reconstruct their own understanding of the learning material. This research provides new insights into design principles for collaborative learning agents in elementary education settings, effective implementation scenarios based on class size, and the future potential of AI-enhanced collaborative learning.

著者
Satomi Tokida
The University of Tokyo, Tokyo, Japan
Koki Usui
AISIN CORPORATION, Aichi, Japan
Godai Tanaka
AISIN CORPORATION, Aichi, Japan
Shin Osuga
AISIN CORPORATION, Aichi, Japan
Masanori Kayano
University of Yamanashi, Yamanashi, Japan
Yuta Itoh
Institite of Science Tokyo, Yokohama, Japan
Yoshio Ishiguro
The University of Tokyo, Tokyo, Japan

会議: CHI 2026

ACM CHI Conference on Human Factors in Computing Systems

セッション: AI for Youth Learning

P1 - Room 129
7 件の発表
2026-04-17 18:00:00
2026-04-17 19:30:00