PaperTok: Exploring the Use of Generative AI for Creating Short-form Videos for Research Communication

2026-01-26

AI Summary

This work addresses the challenge that researchers often lack the time and skills to translate academic findings into accessible content suitable for short-video platforms, thereby limiting the reach and impact of scientific communication. To bridge this gap, we propose the first end-to-end generative AI system that automatically produces diverse video scripts and accompanying audiovisual assets from academic papers, while enabling fine-grained refinement through researcher-provided prompts. Integrating natural language processing with multimodal generation techniques, our approach establishes a novel human-AI collaborative paradigm for scholarly dissemination. Evaluations through a user study (N=18) and crowdsourced assessment (N=100) demonstrate that the system significantly lowers the barrier to science communication and effectively enhances both the informational value and engagement of resulting short videos.

Technology Category

• Natural Language Processing: Generation
• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

The dissemination of scholarly research is critical, yet researchers often lack the time and skills to create engaging content for popular media such as short-form videos. To address this gap, we explore the use of generative AI to help researchers transform their academic papers into accessible video content. Informed by a formative study with science communicators and content creators (N=8), we designed PaperTok, an end-to-end system that automates the initial creative labor by generating script options and corresponding audiovisual content from a source paper. Researchers can then refine based on their preferences with further prompting. A mixed-methods user study (N=18) and crowdsourced evaluation (N=100) demonstrate that PaperTok's workflow can help researchers create engaging and informative short-form videos. We also identified the need for more fine-grained controls in the creation process. To this end, we offer implications for future generative tools that support science outreach.

Problem

• research communication
• short-form videos
• generative AI
• science outreach
• content creation

Innovation

• generative AI
• research communication
• short-form video
• science outreach
• automated content creation