AutiHero: Engaging Parents in Creating Personalized, Multi-path Social Narratives for Autistic Children

Abstract

Social narratives help autistic children understand and navigate social situations through stories. To ensure effective practice, however, they often require significant time and effort from parents in customizing the narrative materials and delivering repeated instructions on them. We present AutiHero, a generative AI (GenAI)-based social narrative system, which supports parents to create personalized, multi-path stories targeting specific behavior of their autistic children, while enabling them to explore behavioral choices and causal consequences together in reading. A two-week deployment study with 16 autistic child-parent dyads showed that parents actively created, adapted, and read stories with their children, with increased confidence in everyday behavioral guidance. Our work contributes real-world-contextualized text+image content creation approaches harnessing GenAI, ensuring user-aligned application in sensitive contexts involving autistic children and their parents.

Figures (7)

• Figure 1: The multi-path structure of the AutiHero stories. In the Challenge page (ⓒ) the child is asked to select one of the given paths (ⓓ or ⓘ). The undesirable paths always have a turning point, Repair (ⓕ), which addresses the negative Consequence (ⓔ) and eventually leads the story to the positive Ending (ⓚ) same as the desirable path.
• Figure 2: Pipelines for generating story text and illustrations. The parent enters the target behavior and selects an interest to be featured in the story (ⓐ). The Narrative generator (ⓑ) produces a draft story, which is then validated and refined by the Content validator (ⓔ) and Text refiner (ⓕ). Next, the Scene description generator (ⓘ) creates scene descriptions for each page, taking the child profile (ⓒ) into account. Finally, with support from the Scene--entity matcher (ⓙ) and Entity visual describer (ⓚ), a multimodal LLM (ⓜ) generates illustrations for each page that remain consistent with the story context.
• Figure 3: Illustrations from participants' stories and how contextual entities were reflected in them.
• Figure 4: Post-study ratings of parent participants on the technology acceptance model (TAM) subscales, evaluating Creator (a) and Reader (b) separately.
• Figure 5: Prompt template for generating story text per topic.