"Can We Detect Substance Use Disorder?": Knowledge and Time Aware Classification on Social Media from Darkweb

TL;DR

This paper develops a knowledge-aware, time-sensitive deep learning approach to analyze social media posts from the dark web, aiming to detect substance use disorder by understanding perceptions and emotional responses to opioids.

Contribution

It introduces a novel combination of drug ontology, sentiment analysis, and temporal neural models to improve substance use disorder detection from dark web social media data.

Findings

Achieved macroF1 score of 82.12 in detecting substance use disorder.

Identified key emotional and sentiment patterns related to different opioids.

Demonstrated the effectiveness of time-aware models in understanding drug-related social media activity.

Abstract

Opioid and substance misuse is rampant in the United States today, with the phenomenon known as the "opioid crisis". The relationship between substance use and mental health has been extensively studied, with one possible relationship being: substance misuse causes poor mental health. However, the lack of evidence on the relationship has resulted in opioids being largely inaccessible through legal means. This study analyzes the substance use posts on social media with opioids being sold through crypto market listings. We use the Drug Abuse Ontology, state-of-the-art deep learning, and knowledge-aware BERT-based models to generate sentiment and emotion for the social media posts to understand users' perceptions on social media by investigating questions such as: which synthetic opioids people are optimistic, neutral, or negative about? or what kind of drugs induced fear and sorrow? or what kind of drugs people love or are thankful about? or which drugs people think negatively about? or which opioids cause little to no sentimental reaction. We discuss how we crawled crypto market data and its use in extracting posts for fentanyl, fentanyl analogs, and other novel synthetic opioids. We also perform topic analysis associated with the generated sentiments and emotions to understand which topics correlate with people's responses to various drugs. Additionally, we analyze time-aware neural models built on these features while considering historical sentiment and emotional activity of posts related to a drug. The most effective model performs well (statistically significant) with (macroF1=82.12, recall =83.58) to identify substance use disorder.