Floor Raiser or Ceiling Limiter? Differential Storytelling Outcomes with a Child-Centric GenAI System Across Individual Differences

2026-06-25

AI Summary

This study investigates the differential impact of generative artificial intelligence (GenAI) on creative writing among children aged 7–12. Employing a within-subjects design, it combines quantitative evaluation and qualitative analysis to compare story quality when children use GenAI systems—featuring keyword-guided story generation and image-to-story regeneration based on a “mechanism-dependent scaffolding” framework—against traditional storyboard-based creation. Findings reveal that GenAI significantly narrows the gap in story quality between high- and low-performing participants by 83.5%, demonstrating a convergence effect that elevates lower performers while constraining higher ones. This effect is selective, manifesting primarily in creativity and content richness. Image regeneration positively predicts narrative structure quality, age moderates preference for semantic distance in keywords, and individual differences emerge in engagement propensity.

Abstract

Generative AI (GenAI) holds promise for democratizing creative literacy, yet whether it benefits all children equally remains unclear. Using a child-centric GenAI storytelling system for children aged 7-12, we conducted a mixed-methods within-subjects experiment (N = 40, Grades 2-6) comparing GenAI-assisted and traditional storyboard conditions. Three findings emerged. First, the GenAI-assisted condition was associated with a floor-raising convergence pattern, with the quality gap narrowing by 83.5%, driven by lower-end support and upper-end constraint mechanisms. This convergence was dimension-selective, improving creativity and richness while leaving coherence and narrative structure tied to baseline performance. Second, younger children more often selected semantically distant keywords while older children preferred semantically closer ones, although engagement orientation varied across individuals regardless of age. Third, image regeneration was positively associated with structural quality dimensions, though this association was attenuated after baseline control. We propose mechanism-contingent scaffolding as a design principle for adaptive GenAI storytelling systems serving diverse children.

Problem

• Generative AI
• child development
• individual differences
• creative literacy
• educational equity

Innovation

• generative AI
• child-centric design
• mechanism-contingent scaffolding
• creative literacy
• individual differences