A Demonstration of AI Personalized Interactive Fiction for Young Children

Abstract

This paper presents a novel high-fidelity prototype designed to enable young children to create personalized, interactive stories using advanced AI technologies. Our approach addresses a gap in existing AI-driven storytelling applications by focusing specifically on young children. The prototype allows children to select story topics using emojis and engages them with vivid multimedia elements including AI-generated illustrations, sounds, and music. Our goal is to foster critical thinking through choice-based narratives that allow children to influence story outcomes. Parents can review and provide feedback on AI-generated media to ensure age-appropriate content. The system integrates large language models (LLMs) for story generation with text-to-image, text-to-sound, and text-to-music AI models to deliver an engaging multimedia storytelling experience. The paper describes the prototype system in conjunction with a story generated by it. Our prototype demonstrates the potential of child-centric AI storytelling tools to positively impact children’s learning and development.

Recommended citation: Lesner, J., Murayama, L., Guizar, T., Phunjamaneechot, P., & Shapiro, D. (2024). Frontiers in Artificial Intelligence and Applications: Vol. 392. ECAI 2024 (pp. 4487-4490). IOS Press.
Download Paper | Download Slides