Recently, students in the University of Washington’s Prosocial Computing Group noticed a trend on social media: People were using generative artificial intelligence to make short science videos. The trouble was that these people weren’t scientists, which, given AI’s proclivity to be convincingly wrong, could accelerate the spread of misinformation. So the lab wondered how to enable scientists and other researchers to better adapt to platforms like TikTok.
“The alternative is that science is being talked about without scientists,” said co-lead author Meziah Ruby Cristobal, a UW doctoral student in human centered design and engineering.
Those discussions led the team to build PaperTok, an AI tool that helps users turn research papers into 45-second videos. A researcher uploads a paper to the tool, which uses Google Gemini to write a short script explaining the paper. The researcher can then iteratively edit the transcript and resulting video clip.
The team presented its research April 17 at the Association for Computing Machinery Conference on Human Factors in Computing Systems in Barcelona.
“For several reasons, most people don’t read research papers,” said senior author Gary Hsieh, a UW professor in human centered design and engineering. “I still have challenges reading papers in fields I’m not familiar with. So we wanted to find a way to quickly turn papers into a format that laypeople would want to engage with, and we wanted to study how they engaged with it.”
Currently, PaperTok is only accessible to users with a paid Google Gemini subscription. Those users can go to the PaperTok site and upload a research paper. The system then presents four options to use as a hook in the video. For instance, a PaperTok video on PaperTok itself begins, “Ever get overwhelmed reading a dense academic paper?”
“To start, we interviewed eight science communicators and content producers about how to make engaging, credible videos,” said co-lead author Donghoon Shin, a UW doctoral student in human centered design and engineering. “We found that hooks are integral to shortform videos. Because you’re competing with other videos online, you have only a few seconds to grab someone’s attention.”
After picking a hook, PaperTok generates a script, which users can edit. In the storyboarding phase, the script is broken into scenes — much like a movie storyboard. Users can keep refining their scripts and video clips. When they’re happy with the result, they can add a byline, which appears at the end along with the paper’s authors.
The team asked 100 online participants and 18 academic participants to compare video from PaperTok with videos from two other PDF-to-video generators. They found PaperTok easy to use and its videos more engaging than those from the other systems. But some had concerns that it was “too AI-ish” — because of AI signs like nonsense text — to want to share publicly, because that may diminish their scholarship’s credibility.
The team plans to keep working on ways to customize the AI-generated video, such as allowing users to draw on specific parts of a scene so that elements change based on their intent.
“The main motivation behind PaperTok was, ‘How can we enable researchers to create engaging short-form videos?’,” Cristobal said. “Because with generative AI tools, anyone can generate a video from a PDF in minutes, and that presents all sorts of problems — misinformation, AI slop. So we wanted to build a tool that keeps humans, ideally experts, involved. If anything, we hope that PaperTok highlights how important people are in science communication.”
Co-authors include Hyeonjeong Byeon, a UW doctoral student in human centered design and engineering; Tze-Yu Chen of Boson AI, who contributed to this research as a UW master’s student; Ruoxi Shang, a UW doctoral candidate in human centered design and engineering; Ruican Zhong, a UW doctoral student in human centered design and engineering; and Tony Zhou, a UW student in computer science. This research was supported by Microsoft AI and the New Future of Work Award, the Google PaliGemma Academic Program GCP Credit Award, and the National Science Foundation CISE Graduate Fellowships.
For more information, contact Hsieh at garyhs@uw.edu, Shin at dhoon@uw.edu and Cristobal at meziah@uw.edu.