AutiHero: Leveraging Generative AI in Social Narratives to Engage Parents in Story-Driven Behavioral Guidance for Autistic Children

2025-09-22

AI Summary

To address the challenges of labor-intensive, time-consuming customization of social narrative materials for home-based autism interventions, this study introduces the first generative AI–based system for personalized social story generation. The system jointly models child-specific interests, target behaviors, and daily contextual scenarios to co-drive large language models (LLMs) for narrative text generation and diffusion models for aligned illustrative image synthesis, producing multimodal, contextually grounded social stories. In a two-week field study involving 16 families, caregivers generated 218 stories, averaging 4.25 stories read per day—significantly increasing intervention frequency and parent–child shared reading quality. This work represents the first systematic application of generative AI to social narrative intervention, enabling highly personalized, low-burden behavioral support for families while enhancing caregiver engagement and children’s social learning outcomes.

Technology Category

• Natural Language Processing: Generation
• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Social narratives are known to help autistic children understand and navigate social situations through stories. To ensure effectiveness, however, the materials need to be customized to reflect each child's unique behavioral context, requiring considerable time and effort for parents to practice at home. We present AutiHero, a generative AI-based social narrative system for behavioral guidance, which supports parents to create personalized stories for their autistic children and read them together. AutiHero generates text and visual illustrations that reflect their children's interests, target behaviors, and everyday contexts. In a two-week deployment study with 16 autistic child-parent dyads, parents created 218 stories and read an average of 4.25 stories per day, demonstrating a high level of engagement. AutiHero also provided an effective, low-demanding means to guide children's social behaviors, encouraging positive change. We discuss the implications of generative AI-infused tools to empower parents in guiding their children's behaviors, fostering their social learning.

Problem

• Creating personalized social narratives requires significant parental time and effort
• Customizing behavioral guidance materials for each autistic child's unique needs
• Supporting parents in effectively guiding autistic children's social behaviors at home

Innovation

• Generative AI creates personalized social narratives
• System customizes stories with child-specific interests
• AI generates both text and visual illustrations