Detecting Opioid Users from Twitter and Understanding Their Perceptions Toward MAT

Opioid (e.g., heroin and morphine) addiction has become one of the largest and deadliest epidemics in the United States. To combat such deadly epidemic, there is an urgent need for novel tools and methodologies to gain new insights into the behavioral processes of opioid addiction and treatment. In this paper, we design and develop an intelligent system named iOPU to automate the detection of opioid users from Twitter. In iOPU, to model the users and posted tweets as well as their rich relationships, we first introduce a structured heterogeneous information network (HIN) for representation. Then we use meta-graph based approach to characterize the semantic relatedness over users. Afterwards, we integrate content-based similarity (i.e., similarity of users' posted tweets) and relatedness depicted by each meta-graph to formulate a similarity measure over users. Further we build a classifier combining different similarities based on different meta-graphs to make predictions. Comprehensive experiments on real sample collections from Twitter are conducted to validate the effectiveness of our developed system iOPU in opioid user detection by comparisons with other baseline methods. The results also demonstrate that knowledge from daily-life social media data mining could promote the practice of Medication Assisted Treatment (MAT) in opioid addiction.