Role-play is widely used to empower autistic children to explore social interaction and dynamics on their own terms, navigating neurotypical social conventions to shape social expressions in ways that align with their own traits and needs, fostering a stronger sense of agency. However, existing approaches typically rely on fixed content, requiring educators to design materials, which creates a significant burden on manual preparation. According to insights from a formative study, we developed GenRole, a generative AI system that enables educators to design personalized role play class activities. GenRole supports a progression from simple to complex interactions and allows for personalization of characters, settings, and dialogues that meet the needs of autistic learners. We conducted a pilot study with 16 educators, followed by a two-week evaluation study with 11 autistic children and their teachers. Results show that GenRole enhances the efficiency and flexibility of role play design while improving instructional support, offering design insights for creating personalized components that help educators deliver more engaging and individualized social interaction learning for autistic children.
ACM CHI Conference on Human Factors in Computing Systems