A Weak Supervision Approach for Monitoring Recreational Drug Use Effects in Social Media
Lucía Prieto-Santamaría, Alba Cortés Iglesias, Claudio Vidal Giné, Fermín Fernández Calderón, Óscar M. Lozano, Alejandro Rodríguez-González
arXiv Preprint Archive September 18, 2025 via arXiv
Summary
AI-generated from the abstractSocial media posts on Twitter can reveal how people describe the effects of recreational drugs like ecstasy, GHB, and 2C-B. By analyzing over 92,000 tweets using slang terms and biomedical concept extraction, researchers identified whether each post reported a positive or negative effect. Machine learning classifiers, particularly eXtreme Gradient Boosting with cost-sensitive learning, predicted tweet polarity with high accuracy (F1 = 0.885, AUPRC = 0.934). The findings suggest that Twitter data can detect substance-specific effects and support real-time drug monitoring and characterization of effects.
Study at a glance
| Characteristics | Observational study using social media data Peer reviewed |
|---|---|
| Sample size | 92,000 |
| Population | Tweets mentioning ecstasy, GHB, or 2C-B |
| Keywords | Cs.lg |
| Key finding | Machine learning models can classify Twitter posts about recreational drugs as reporting positive or negative effects with high accuracy, enabling real-time pharmacovigilance. |
Abstract
Understanding the real-world effects of recreational drug use remains a critical challenge in public health and biomedical research, especially as traditional surveillance systems often underrepresent user experiences. In this study, we leverage social media (specifically Twitter) as a rich and unfiltered source of user-reported effects associated with three emerging psychoactive substances: ecstasy, GHB, and 2C-B. By combining a curated list of slang terms with biomedical concept extraction via MetaMap, we identified and weakly annotated over 92,000 tweets mentioning these substances. Each tweet was labeled with a polarity reflecting whether it reported a positive or negative effect, following an expert-guided heuristic process. We then performed descriptive and comparative analyses of the reported phenotypic outcomes across substances and trained multiple machine learning classifiers to predict polarity from tweet content, accounting for strong class imbalance using techniques such as cost-sensitive learning and synthetic oversampling. The top performance on the test set was obtained from eXtreme Gradient Boosting with cost-sensitive learning (F1 = 0.885, AUPRC = 0.934). Our findings reveal that Twitter enables the detection of substance-specific phenotypic effects, and that polarity classification models can support real-time pharmacovigilance and drug effect characterization with high accuracy.