Themes in TikTok Videos Featuring Little Cigars and Cigarillos: Content Analysis

Vassey, Julia; Donaldson, Scott; Dormanesh, Banafshe; Allem, Jon-Patrick

doi:10.2196/42441

Cited by 10 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The removal of posts that violate the platform’s community guidelines could be accomplished through the flagging of suspected violations by content moderators. 11 Studies 13 show that while a small fraction of tobacco-related content gets removed from the platform, most of it remains available and accessible to youth, indicating that further improvement in the enforcement of community guidelines is necessary. In addition, federal authorities could regulate influencer e-cigarette-related marketing, because influencers are regarded as more trusted and authentic sources of content than traditional advertising 46 and could diminish adolescents’ harmful perceptions of e-cigarettes promoted by influencers.…”

Section: Discussionmentioning

confidence: 99%

“…Qualitative content analysis using human coders is common in identifying themes in tobacco-related images or videos on social media. 13 , 20 , 21 One limitation of this method is the small sample size due to the time burden of review. Applying advanced computational methods is a valuable methodological contribution to tobacco control research, allowing for automated analysis of visual posts of big data-scale sample sizes.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Scalable Surveillance of E-Cigarette Products on Instagram and TikTok Using Computer Vision

Vassey,

Kennedy,

Herbert Chang

et al. 2023

Nicotine and Tobacco Research

Self Cite

View full text Add to dashboard Cite

Introduction Instagram and TikTok, video-based social media platforms popular among adolescents, contain tobacco-related content despite the platforms’ policies prohibiting substance-related posts. Prior research identified themes in e-cigarette-related social media posts using qualitative or text-based machine learning methods. We developed an image-based computer vision model to identify e-cigarette products in social media images and videos. Methods We created a dataset of 6,999 Instagram images labeled for 8 object classes: mod or pod devices, e-juice containers, packaging boxes, nicotine warning labels, e-juice flavors, e-cigarette brand names, and smoke clouds. We trained a DyHead object detection model using a Swin-Large backbone, evaluated the model’s performance on 20 Instagram and TikTok videos, and applied the model to 14,072 e-cigarette-related promotional TikTok videos (2019-2022; 10,276,485 frames). Results The model achieved the following mean average precision scores on the image test set: e-juice container: 0.89; pod device: 0.67; mod device: 0.54; packaging box: 0.84; nicotine warning label: 0.86; e-cigarette brand name: 0.71; e-juice flavor name: 0.89; and smoke cloud: 0.46. The largest number of TikTok videos – 9,091 (65%) - contained smoke clouds, followed by mod and pod devices detected in 6,667 (47%) and 5,949 (42%) videos respectively. Prevalence of nicotine warning labels was the lowest, detected in 980 videos (7%). Conclusions Deep learning-based object detection technology enables automated analysis of visual posts on social media. Our computer vision model can detect the presence of e-cigarettes products in images and videos, providing valuable surveillance data for tobacco regulatory science. Implications Prior research identified themes in e-cigarette-related social media posts using qualitative or text-based machine learning methods. We developed an image-based computer vision model to identify e-cigarette products in social media images and videos. We trained a DyHead object detection model using a Swin-Large backbone, evaluated the model’s performance on 20 Instagram and TikTok videos featuring at least two e-cigarette objects, and applied the model to 14,072 e-cigarette-related promotional TikTok videos (2019-2022; 10,276,485 frames). The deep learning model can be used for automated, scalable surveillance of image- and video-based e-cigarette-related promotional content on social media, providing valuable data for tobacco regulatory science. Social media platforms could use computer vision to identify tobacco-related imagery and remove it promptly, which could reduce adolescents’ exposure to tobacco content online.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Scalable Surveillance of E-Cigarette Products on Instagram and TikTok Using Computer Vision

Vassey,

Kennedy,

Herbert Chang

et al. 2023

Nicotine and Tobacco Research

Self Cite

View full text Add to dashboard Cite

show abstract

“…This can affect the cooperation between the university and the local community and create obstacles in the implementation of future KKN programs. This analysis highlights the importance of awareness and responsibility among social media users, particularly concerning the content they share (Vassey et al, 2022). TikTok content has the potential to influence public opinion and trigger significant events.…”

Section: Content Of Tiktok Videosmentioning

confidence: 88%

Analysis Of Tiktok Video Content In The Incident Of UNP Student Eviction By Residents: A Case Study Of Perceptions And Impacts

Desiana

2024

FIJC

View full text Add to dashboard Cite

This study aims to analyze video content on TikTok related to incidents of KKN UNP students being expelled by residents and examine their perceptions and impacts in a social context. In this case study, an in-depth review of the video content made by UNP KKN students and residents involved in the incident was carried out. The research method used is video content analysis and a case study approach. Through an analysis of the messages and narration in the video content on TikTok regarding the expulsion incident, it is described and interpreted. The results of this study reveal that the messages in the video content play an important role in shaping the narrative and influencing the people's perspective on the event. This research also found the factors that influence the perception and impact of video content on TikTok as well as understanding of the role of social media in shaping public opinion and its effect on social dynamics, such as people's perception of the video content and its impact through public attitudes.

show abstract

“…In addition to characterizing flavors, they have lower taxation 6,7 and fewer units per pack, which makes them affordable and appealing to consumers, including young people [8][9][10] . Their appeal to young people is even more concerning given their promotion on social media such as TikTok and Instagram 11,12 .…”

Section: Introductionmentioning

confidence: 99%

Circumventing cigarette regulation: Product characteristics of cigarette-like cigarillos on the Dutch market

Pennings¹,

Pauwels²,

Schenk³

et al. 2023

Tob. Induc. Dis.

View full text Add to dashboard Cite

INTRODUCTION Cigarillos have been reported to provide an alternative to cigarettes with a characterizing flavor, which are banned in the European Union. Additionally, they are cheaper than cigarettes. To better inform policy making, we wanted to gain better insight into the market situation for cigarillos in the Netherlands. METHODS We analyzed product data notified by manufacturers via the European Common Entry Gate system (EU-CEG), as extracted on the 1 June 2022. First, we identified parameters that allowed classifying cigarillos into cigar-like, cigarettelike and intermediate-type cigarillos. Next, we compared product characteristics for these groups. RESULTS We identified five parameters that allowed classifying cigarillos into subtypes: product weight, filter presence, leaf tobacco percentage in the product, flue-cured tobacco percentage in the product, and the number of flavorings. Almost a quarter (71/285) of the cigarillos on the Dutch market were classified as cigarette-like. Compared to other cigarillo types, these have a high number of flavorings (average n=43), including many sweet and fruity flavorings. The package types of cigarette-like cigarillos resemble those of cigarettes. However, 85% of the cigarette-like cigarillos are available in smaller pack sizes than allowed for cigarettes. When comparing data over the period 2019-2022, we found a decrease in the number of cigar-like cigarillos and an increase in the number of cigarette-like cigarillos, which hints at a shift in the market composition. CONCLUSIONS Cigarette-like cigarillos can provide a way to evade cigarette regulation. Moreover, their characteristics make them attractive for consumers, including young people. Regulators should consider amending regulations to close the regulatory loopholes that allow evading tobacco legislation.

show abstract

Themes in TikTok Videos Featuring Little Cigars and Cigarillos: Content Analysis

Cited by 10 publications

References 25 publications

Scalable Surveillance of E-Cigarette Products on Instagram and TikTok Using Computer Vision

Scalable Surveillance of E-Cigarette Products on Instagram and TikTok Using Computer Vision

Analysis Of Tiktok Video Content In The Incident Of UNP Student Eviction By Residents: A Case Study Of Perceptions And Impacts

Circumventing cigarette regulation: Product characteristics of cigarette-like cigarillos on the Dutch market

Contact Info

Product

Resources

About