Stitching, dueting, and playing with science on TikTok: An AI-powered multimodal approach to understanding interactive science videos and audience engagement

Authors

  • Yuhan Li Department of Communication and Media, University of Michigan, Ann Arbor, MI, USA https://orcid.org/0000-0002-8992-1601
  • Annie Li Zhang Center for an Informed Public, University of Washington, Seattle, WA, USA
  • Hang Lu Department of Communication and Media, University of Michigan, Ann Arbor, MI, USA

DOI:

https://doi.org/10.5117/CCR2026.4.2.LI

Keywords:

short-video, science communication, TikTok, multimodal communication, public engagement

Abstract

TikTok offers interactive features, such as stitch, duet, and reply-to, that enable creators to respond to others and co-create science content, but it remains unclear whether these features translate into participatory science communication in practice. We developed an AI-powered framework to analyze 2,796 TikTok science short videos with 31,782 image frames and 2,796 audio files, examining how interactive features intersect with communicator identity, communication objectives, and audio-visual presentation strategies. We found that interactive videos were a small share of the overall science videos, yet they showed both promise and risks of participatory science communication: they were actively adopted by scientists and influencers and often used to inform the public and debunk misinformation, but they also facilitated the circulation of pseudoscience. Using latent class analysis, we identified four recurring styles of interactive videos: professional-led explanatory science, ordinary user-led personal commentary on science, influencer-led entertainment or experimental science, and ordinary user-led visual science. This study enriches our understanding of participatory science communication on TikTok and offers an AI-powered analysis framework for studying multimodal science messages on short-video platforms.

Author Biographies

  • Yuhan Li, Department of Communication and Media, University of Michigan, Ann Arbor, MI, USA

    Yuhan Li (M.A., Tsinghua University) is a third-year Ph.D. student at the Department of Communication and Media at the University of Michigan—Ann Arbor. She is interested in science communication, environmental communication, and computational social science. She primarily uses experimental and computational methods to study public understanding and acceptance of science (e.g., climate change) and technologies (e.g., AI) and how people’s understanding of science and technology drives their perceptions, attitudes, and behaviors.

  • Annie Li Zhang, Center for an Informed Public, University of Washington, Seattle, WA, USA

    Annie Zhang is a postdoctoral scholar at the Center for an Informed Public at the University of Washington. Her research lies at the intersection of science communication, digital & social media, and strategic communication, particularly considering the changing nature of science communication and its social, political, and persuasive implications.

  • Hang Lu, Department of Communication and Media, University of Michigan, Ann Arbor, MI, USA

    Hang Lu (Ph.D., Cornell University) is an Associate Professor in the Department of Communication and Media, University of Michigan—Ann Arbor. His research revolves around understanding how different audience segments respond to media messages regarding science, health, environmental, and risk issues, and how these messages can be crafted to maximize their effectiveness.

Downloads

Published

2026-07-14

Issue

Vol. 8 No. 4 (2026): Special Issue: Computational Analysis of Short Video

Section

Special Issue: Short Video

How to Cite

Li, Y., Zhang, A. L., & Lu, H. (2026). Stitching, dueting, and playing with science on TikTok: An AI-powered multimodal approach to understanding interactive science videos and audience engagement. Computational Communication Research, 8(4). https://doi.org/10.5117/CCR2026.4.2.LI