Artificial intelligence innovations in substance use prevention on social media: A scoping review

The article provides a broad overview of artificial intelligence (AI) and machine learning applications for substance use prevention on social media. Over recent years, the primary focus of these technologies has centered on descriptive tasks, such as trend monitoring and risk prediction, heavily relying on natural language processing. While the potential for AI in public health is well recognized, reports consistently highlight significant barriers, including language ambiguity, data imbalance, and ethical concerns. The current research landscape reflects a tension between AI's theoretical promise and the practical limitations of its real-world implementation. The successful deployment of computational models to evaluate prevention campaigns is a notable starting point. However, the development of proactive, cross-platform solutions is still evolving. Emphasizing explainable AI and human validation will continue to play an important role in advancing this field. There are promising indications that future research will move toward addressing these technical limitations and developing locally adapted, interactive interventions to enhance global substance use prevention.