From Words to Wonder: Designing and Evaluating an AI-Empowered Creative Storytelling System for Elementary
Childre
Min Fan, Xinyue Cui, Wanqing Ma, Haiyan Li, Xin Tong, Lin Yang, Yonghui Wang
Abstract
While several digital tools exist for children's creative storytelling, few have explored how generative AI
can enhance storytelling quality. Our formative research identified five design requirements for AI-powered
storytelling tools for elementary students. We developed a system named StoryPrompt that enables children to
co-create stories and comics with AI, boosting literacy and creativity. Pilot tests with children and HCI
experts demonstrated good usability and positive learning experiences. In a mixed-methods evaluation with 40
children from Grades 2-6, we found that StoryPrompt significantly improved storytelling creativity and
richness, compared to the storyboard method. Observations indicated more purposeful planning and strategic
use of AI-generated words and images, facilitating efficient exploration of storytelling alternatives. While
children preferred AI images, they recognized the limitations in representing storytelling details. Teacher
interviews highlighted the system's motivational potential and classroom flexibility. We discuss the
benefits and considerations of using generative AI to enhance creative storytelling for children.