AI system helps create personalized social stories for autistic children
AI-Assisted Social Story Intervention for Special Education: The Design of AdaptED Stories
Human-Computer Interaction
Summary
Autistic children often use Social Stories to understand daily situations better, but making these stories takes a lot of time for teachers. The authors developed AdaptED Stories, a tool that uses AI to draft these stories with text and pictures based on each child’s profile, letting teachers review and change them. This helps teachers make stories faster and more suited to each child’s needs while still keeping control over the content. Their study showed the system is useful and highlights the need to respect cultural and learner differences when using AI tools in special education.
What this means in practice
- •For special education practitioners: Create personalized Social Stories more efficiently using AI drafts that practitioners can edit before sharing with learners.
- •For educational technology developers: Design tools that combine AI generation with expert review to support personalized learning content and session tracking.
Authors
Buyankhishig Enkhjargal, Himanshi Lalwani, Hanan Salam
Abstract
Social Stories are widely used to support autistic children in understanding and preparing for everyday situations, but creating stories that are appropriately tailored to each child's needs remains labor-intensive for practitioners. Existing digital tools support story assembly and delivery, but much of the work of writing, visual preparation, and personalization remains manual. Recent AI-based approaches have enabled automated story generation, yet offer limited support for practitioner oversight, context-sensitive personalization, and the use of supportive visuals grounded in individual learner profiles. We present AdaptED Stories, a practitioner-guided system for authoring, personalizing, and delivering Social Stories in special-education contexts. The system uses student profiles to draft story text and visuals, supports review and refinement by practitioners, and includes reading-session support with comprehension activities and session records. We report findings from a practitioner-informed design process, assessments of generated stories and visuals, and a usability study with seven special-education practitioners. Our findings suggest that AI assistance can reduce story-preparation burden and support more individualized story creation, alongside the importance of practitioner oversight, cultural and contextual specificity, and designing for varied learner needs. These findings contribute design implications for AI-assisted accessibility tools in special-education.