Researchers at the University of Washington’s Prosocial Computing Group have launched PaperTok, an AI-powered platform designed to convert dense academic research papers into 45-second TikTok science videos. The tool, which utilizes Google’s Gemini, aims to bridge the gap between complex scientific findings and general public consumption by automating the scriptwriting and video storyboarding process.
How PaperTok automates science communication
The platform functions by streamlining the transition from a PDF document to a social media-ready clip. Users upload a scientific paper, which the system then analyzes to suggest four potential “hooks” for the video. Once a hook is selected, the tool generates a draft script that users can manually refine for tone and voiceover.
After the script is finalized, the platform breaks the content into a storyboard format, generating corresponding video clips for each scene. The process concludes with the automatic generation of screen credits, ensuring that the original authors of the research are properly cited. Users retain the ability to add their own bylines before merging the scenes into a final, shareable short-form video.
Why researchers are targeting social media
The initiative stems from a growing concern regarding the accuracy of AI-generated science content on social platforms. Gary Hsieh, a professor in human centered design and engineering at the University of Washington and the senior author of the project, noted that many people do not read research papers because they have challenges reading papers in fields they are not familiar with.
The project was formally presented in April at the Association for Computing Machinery Conference on Human Factors in Computing Systems held in Barcelona. PaperTok is currently only accessible with a paid Google Gemini subscription.
Future implications for academic dissemination
The move toward short-form video synthesis represents a shift in how academic institutions approach public engagement. Currently, the primary challenge remains balancing the brevity of a 45-second clip with the complexity of peer-reviewed data.
Frequently Asked Questions
Is PaperTok free to use?
No, PaperTok is currently only accessible with a paid Google Gemini subscription.
Can I edit the videos generated by the tool?
Yes. Users can refine and edit the scripts and matching video clips within the platform before finalizing the output.
Who created PaperTok?
The tool was developed by researchers at the University of Washington’s Prosocial Computing Group, with Gary Hsieh serving as the senior author.
Are you interested in how AI is changing the way we consume information? Subscribe to our newsletter for the latest updates on emerging technology or share your thoughts on the future of science communication in the comments below.
