Generative AI in a new era of computer model-informed tobacco research: a short report

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Accuracy: 87% (nicotine vaping), 96% (cannabis vaping), 99% (fashion), 96% (entertainment), 98% (healthy lifestyle)

• Primary Outcome: AI model accuracy for content detection across five categories

• Nnt Or Sensitivity: Sensitivity and specificity not reported; only overall accuracy provided

• Confidence Interval: Not reported

Clinical Application

Technically feasible but requires access to commercial AI platforms and expertise in prompt engineering Relevant to TGA tobacco advertising surveillance and ACMA social media monitoring; could support Australian tobacco control policy development Public health researchers and tobacco control specialists monitoring social media content

Abstract

BACKGROUND: Social media influencers who promote e-cigarettes on Instagram or TikTok for tobacco brands use marketing tactics to increase the appeal of their promotional content, for example, depicting e-cigarettes alongside healthy lifestyle or entertainment imagery that could decrease youths' risk perceptions of e-cigarettes. Monitoring the prevalence of such content on social media using computer vision and generative AI (artificial intelligence) can provide valuable data for tobacco regulatory science (TRS). METHODS: We selected 102 Instagram and TikTok videos posted by micro-influencers in 2021-2024 who promoted e-cigarettes alongside posts featuring four themes: cannabis, entertainment, fashion or healthy lifestyle. We used OpenAI's GPT-4o multimodal large-scale visual linguistic model to detect the presence of nicotine vaping, cannabis vaping, fashion, entertainment and healthy lifestyle. The model did not require any additional training and improved its performance as we modified the text prompt. RESULTS: The model's accuracy was 87% for nicotine vaping, 96% for cannabis vaping, 99% for fashion, 96% for entertainment and 98% for healthy lifestyle. CONCLUSIONS: Generative AI can achieve accurate object detection with zero-shot learning (no additional training of the pretrained model). This model can be applied to big data-scale sample sizes of images and videos to detect e-cigarette-related and other substance-related promotional content and contexts (eg, healthy lifestyle) used for the promotion of these products on social media, providing valuable data for TRS.

References

1. 1.Vassey, J., Kennedy, C. J., Chang, H. C., & Unger, J. B. (2024). Generative AI in a new era of computer model-informed tobacco research: a short report. Tobacco Control. https://doi.org/10.1136/tc-2024-058887