PedaCo-Gen: Scaffolding Pedagogical Agency in Human-AI Collaborative Video Authoring

TL;DR

PedaCo-Gen is a human-AI collaborative system for creating instructional videos that enhances quality and pedagogical agency by integrating interactive review phases based on multimedia learning principles.

Contribution

It introduces an interactive Intermediate Representation phase enabling educators to refine AI-generated video blueprints, improving instructional quality and user experience.

Findings

Significantly improved video quality across topics and principles.

Participants reported high efficiency and perceived AI guidance as a pedagogical scaffold.

The system enhances educator agency in AI-assisted video creation.

Abstract

While advancements in Text-to-Video (T2V) generative AI offer a promising path toward democratizing content creation, current models are often optimized for visual fidelity rather than instructional efficacy. This study introduces PedaCo-Gen, a pedagogically-informed human-AI collaborative video generating system for authoring instructional videos based on Mayer's Cognitive Theory of Multimedia Learning (CTML). Moving away from traditional "one-shot" generation, PedaCo-Gen introduces an Intermediate Representation (IR) phase, enabling educators to interactively review and refine video blueprints-comprising scripts and visual descriptions-with an AI reviewer. Our study with 23 education experts demonstrates that PedaCo-Gen significantly enhances video quality across various topics and CTML principles compared to baselines. Participants perceived the AI-driven guidance not merely as a set of instructions but as a metacognitive scaffold that augmented their instructional design expertise, reporting high production efficiency (M=4.26) and guide validity (M=4.04). These findings highlight the importance of reclaiming pedagogical agency through principled co-creation, providing a foundation for future AI authoring tools that harmonize generative power with human professional expertise.