Leveraging Large Language Models to Identify Engagement-Driving Features in Vaping-Related TikTok Videos: Cross-Sectional Study
Journal of Medical Internet Research · 2025
DOI: 10.2196/76265 ↗Kurz gefasst
Querschnittstudie in der Zeitschrift Journal of Medical Internet Research, 2025. Verfasst von Zidian Xie und 7 weiteren Autor:innen. Beteiligte Einrichtung: Clinical and Translational Science Institute, University of Rochester, 265 Crittenden Boulevard CU 420708, Rochester, NY, 14642-0708, United States, …. Hauptthemen laut MEDLINE: Vaping, Social Media, Video Recording. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NCI NIH HHS, NCATS NIH HHS.
Abstract (Originalsprache)
Background
Electronic cigarette (e-cigarette) use is prevalent in youth and young adults in the United States. TikTok (ByteDance), a popular social media platform among youth and young adults, has become a key avenue for disseminating e-cigarette-related videos, with promotional videos constituting the predominant form.
Objective
This study aimed to identify key e-cigarette-related TikTok video features associated with high user engagement to assist with future video design for vaping prevention campaigns.
Methods
We collected 1487 e-cigarette-related TikTok videos and related metadata posted between January 2023 and January 2024 using the TikTok API (application programming interface). We applied large language models GPT-4 and Video-LLaMA to extract video features (eg, promotion content, background, perceived sex, lifestyle, talking, cartoon, vaping tricks, and containing emojis) from e-cigarette-related TikTok videos. We randomly selected and hand-coded 25 videos to check the accuracy of 2 models in identifying these video features. We used a linear mixed effects model with random intercept to identify significant video features associated with high TikTok user engagement ([likes+shares+comments]/views).
Results
Compared to the Video-LLaMA model, the GPT-4 model exhibited higher accuracy (83%‐100% vs 24%‐88%) in video feature identification. Notably, video backgrounds in cars (rate ratio [RR]=3.91, 95% CI 1.25‐12.20; P =.009) demonstrated significantly higher user engagement than in public spaces. Moreover, videos featuring young adults (RR=1.24, 95% CI 1.00‐1.53; P =.048), talking (RR=1.63, 95% CI 1.30‐2.05; P
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Clinical and Translational Science Institute, University of Rochester, 265 Crittenden Boulevard CU 420708, Rochester, NY, 14642-0708, United States, 1 5852767285.
- Department of Computer Science, University of Rochester, Rochester, NY, United States.
- Goergen Institute for Data Science and Artificial Intelligence, University of Rochester, Rochester, NY, United States.
- Department of Pediatrics, University of Rochester, Rochester, NY, United States.
- Department of Surgery, University of Rochester, Rochester, NY, United States.
Förderung
- NCI NIH HHS
- NCATS NIH HHS
Zitieren
APA
Xie, Z., Korrapolu, N. K., Dubey, A., Song, L., Xu, C., Wilson, K. M., Cupertino, A., & Li, D. (2025). Leveraging Large Language Models to Identify Engagement-Driving Features in Vaping-Related TikTok Videos: Cross-Sectional Study. Journal of Medical Internet Research. https://doi.org/10.2196/76265
Vancouver
Xie Z, Korrapolu NK, Dubey A, Song L, Xu C, Wilson KM, et al. Leveraging Large Language Models to Identify Engagement-Driving Features in Vaping-Related TikTok Videos: Cross-Sectional Study. Journal of Medical Internet Research. 2025. doi:10.2196/76265
BibTeX
@article{Xie2025,
author = {Xie, Zidian and Korrapolu, Nanda Kishore and Dubey, Amisha and Song, Luchuan and Xu, Chenliang and Wilson, Karen M and Cupertino, AnaPaula and Li, Dongmei},
title = {Leveraging Large Language Models to Identify Engagement-Driving Features in Vaping-Related TikTok Videos: Cross-Sectional Study},
journal = {Journal of Medical Internet Research},
year = {2025},
doi = {10.2196/76265}
}
EUVIMED