Using social media to spot trends in drug use and overdoses

Mining Social Media Big Data for Toxicovigilance: Studying Substance Use via Natural Language Processing and Machine Learning Methods

NIH-funded research Emory University · NIH-11364666

This project uses computer language tools to scan public social media posts for early signs of dangerous drug trends that affect people with substance use or their communities.

Quick facts

Grant typeR01 grant
Study typeNIH-funded research
Funding institutionEmory University NIH-funded
Lab location1 site (Atlanta, United States)
Project IDNIH-11364666 on NIH RePORTER

What this research studies

This project looks at public social media posts about drug use and uses natural language processing and machine learning to find patterns and emerging threats. It focuses on mentions of high-risk drugs like fentanyl, methamphetamine, and other novel synthetic substances, and compares trends across regions, age groups, and rural versus urban areas. The team tracks changes over time, including shifts that happened during the COVID-19 pandemic, to provide faster signals than traditional reporting systems. The work analyzes aggregated public posts and does not require you to enroll or attend clinic visits.

Who could benefit from this research

Good fit: The data come from public social media users, so people who post publicly about substance use, overdoses, or treatment experiences are the sources of information for this project.

Not a fit: People who do not use social media, keep their accounts private, or live in areas with low online representation are unlikely to see direct benefits from this project's findings.

Why it matters

Potential benefit: If successful, the work could give health services and communities earlier warnings about dangerous drugs and help target prevention and treatment where it's needed most.

How similar studies have performed: Previous research has shown social media can reveal emerging drug trends and overdose signals, but using advanced NLP and machine learning for systematic toxicovigilance at scale is still novel and developing.

Where this research is happening

Atlanta, United States

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.