Leveraging Large Language Models to Analyze Emotional and Contextual Drivers of Teen Substance Use in Online Discussions

2025-01-23

AI Summary

This study investigates how adolescents’ social media emotional expressions interact with socio-environmental contexts to influence substance use initiation (tobacco, alcohol, drugs). Method: Leveraging large language models, we conducted semantic parsing, joint emotion-topic modeling, and supervised learning on adolescent social media posts to quantify interactions between discrete emotions (e.g., sadness, guilt, joy) and contextual domains (family, peers, school). Contribution/Results: We identify guilt as a novel protective factor—first empirically demonstrated in this domain. Peer pressure amplifies the risk associated with negative emotions, whereas family/school support and positive affect exert significant buffering effects. We propose a new “emotion–environment co-intervention” paradigm, validated via heatmap-based visualization and predictive analytics. Our model accurately isolates core predictive features of substance-related posts, offering both theoretical grounding and scalable technical pathways for precision prevention.

Technology Category

• Application Domains: Humanities & Computational Social Science
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• User Modeling, Personalization and Recommendation: Social recommender systems and personalization for the social Web
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Adolescence is a critical stage often linked to risky behaviors, including substance use, with significant developmental and public health implications. Social media provides a lens into adolescent self-expression, but interpreting emotional and contextual signals remains complex. This study applies Large Language Models (LLMs) to analyze adolescents' social media posts, uncovering emotional patterns (e.g., sadness, guilt, fear, joy) and contextual factors (e.g., family, peers, school) related to substance use. Heatmap and machine learning analyses identified key predictors of substance use-related posts. Negative emotions like sadness and guilt were significantly more frequent in substance use contexts, with guilt acting as a protective factor, while shame and peer influence heightened substance use risk. Joy was more common in non-substance use discussions. Peer influence correlated strongly with sadness, fear, and disgust, while family and school environments aligned with non-substance use. Findings underscore the importance of addressing emotional vulnerabilities and contextual influences, suggesting that collaborative interventions involving families, schools, and communities can reduce risk factors and foster healthier adolescent development.

Problem

• Teenagers
• Social Media
• Substance Use

Innovation

• Natural Language Processing
• Emotional State Analysis
• Prevention Strategies for Substance Use