Skip to main content

ETHNOS_APP

Home • Search • Journals • List 0

Identification and Classification of Images in e-Cigarette-Related Content on TikTok

Unsupervised Machine Learning Image Clustering Approach

Bibliographic Data

ID21645274
AuthorsJuhan Lee (0000-0003-0860-3327, Department of Psychiatry, Yale University School of Medicine, New Haven, CT, United States, corresponding author), Dhiraj Murthy (0000-0001-9734-1124, School of Journalism and Media, University of Texas Austin, Austin, TX, United States), Rachel R Ouellette (0000-0001-6982-0830, Yale University), Rachel Ouellette (Department of Psychiatry, Yale University School of Medicine, New Haven, CT, United States), Tanvi Anand (0000-0001-5976-8581, School of Journalism and Media, University of Texas Austin, Austin, TX, United States), Grace Kong (0000-0002-9269-3435, Department of Psychiatry, Yale University School of Medicine, New Haven, CT, United States)
Year2025
Volume60
Issue5
Pages677-683
Publication date2025-04-16
Peer ReviewedYes
Open AccessNo
TypeARTICLE
VenueSubstance Use & Misuse (JOURNAL)
Journal identifiersISSN: 1082-6084 • E-ISSN: 1532-2491
PublisherInforma UK Limited (PUBLISHER • GB)
DOI10.1080/10826084.2024.2447415
PMID40019898
OpenAlexW4405953401
LanguageEN
Citations received1
References cited26

Background Previous studies identified e-cigarette content on popular video and image-based social media platforms such as TikTok. While machine learning approaches have been increasingly used with text-based social media data, image-based analysis such as image-clustering has been rarely used on TikTok. Image clustering can identify underlying patterns and structures across large sets of images, enabling more streamlined distillation and analysis of visual data on TikTok. This study used image-clustering approaches to examine e-cigarette-related images on TikTok.Methods We searched for 13 hashtags related to e-cigarettes in November 2021 (e.g., vape, vapelife). We scraped up to 1000 posts per hashtag depending on the number of available posts, for 12,599 posts in total. After randomly selecting 13% of posts and excluding non-English (N = 278), non-e-cigarette-related (N = 88), and unavailable posts (i.e., posts that the uploader deleted) (N = 286), N = 838 e-cigarette TikTok images were included in our image clustering model. Using quantitative (e.g., silhouette scores) and qualitative evaluations, we categorized clusters into overarching themes based on the types of e-cigarette content depicted within each cluster.Results We identified N = 20 clusters, forming four overarching themes: (1) vapor clouds (e.g., vape tricks, vaping and exhaling vapor clouds, being captured as clouds from the mouth or nose or around the face); (2) devices (e.g., content presenting e-cigarette devices or individuals demonstrating use or modification of devices); (3) text (e.g., e-cigarette-related text inserted within images such as jokes); (4) other (i.e., e-cigarette-related images clustered based on other image characteristics such as color tones).Conclusions This study using the state-of-the-art image-clustering method successfully identified various e-cigarette-related images on TikTok. This study suggests that novel methodologies can be helpful to tobacco regulatory agencies looking to conduct rapid surveillance of e-cigarette content on social media

Biology · Cluster analysis · k-means clustering · Computer Science · Nicotinic Acetylcholine Receptors Study · Smoking Behavior and Cessation · Social Media in Health Education · Artificial Intelligence

  • Mapping the E-Cigarette Discussion

    Qi Liu, Liu Q•Substance Use & Misuse•2026

  • Effects of Social Media on Adolescents’ Willingness and Intention to Use E-Cigarettes

    Open Access•Erin A Vogel, Danielle E Ramo et al.•Nicotine & Tobacco Research•2021

  • Media Effects

    Patti M Valkenburg, Jochen Peters et al.•Annual Review of Psychology•2016

  • Social media e-cigarette exposure and e-cigarette expectancies and use among young adults

    Open Access•Pallav Pokhrel, Pebbles Fagan et al.•Addictive Behaviors•2018

  • Association Between Exposure to Tobacco Content on Social Media and Tobacco Use

    Open Access•Scott Donaldson, Scott I Donaldson et al.•JAMA Pediatrics•2022

  • Understanding the Associations Between Adolescents’ Exposure to E-Cigarette Information and Vaping Behavior Through the Theory of Planned Behavior

    Qinghua Yang•Health Communication•2024

  • Promotion of E-Cigarettes on TikTok and Regulatory Considerations

    Open Access•Jonine Jancey, Tama Leaver et al.•International Journal of…•2023

  • Vaping on TikTok

    Tianze Sun, Carmen C W Lim et al.•Tobacco Control•2021

  • Understanding e-cigarette content and promotion on YouTube through machine learning

    Grace Kong, Alex Sebastian Schott et al.•Tobacco Control•2022

  • Social Cognitive Theory of Mass Communication

    Albert Bandura•Media Psychology•2001

Unique citing works1
Citations per year1
Citation span2026 - 2026 (1)
Citation velocitycurrent
Highly citedNo
Citation typesNeutral: 1
Ethnos_APP • Open Source Project • MIT License • Frontend v2.0.0 • Privacy and Cookies • API Documentation: api.ethnos.app/docs • API Source Code: GitHub • DOI: 10.5281/zenodo.17049435 • Frontend Source Code: GitHub • DOI: 10.5281/zenodo.17050053 • cruz.rio.br • Expectantes Misericordiae