Illicit online pharmacies allow the purchase of opioids online without a prescription. Such pharmacies also leverage social media platforms such as Twitter as a promotion and marketing tool with the intent of reaching out to a larger, potentially younger and more vulnerable demographics of the population. Given the grave impact of abusing opioids, it is important to identify the relevant content on social media and exterminate their presence as quickly as possible. The sheer volume of tweets and the variability in their content necessitates the use machine learning models that can handle large amounts of noisy data in a robust manner and efficiently identify the tweets that promote and market opioids with high precision. This talk will focus on the methods and models used for data collection, feature engineering and modeling required to identify tweets that promote and market opioids. We use an unsupervised topic modeling based methodology to isolate tweets that promote and market opioids. We then study the metadata characteristics of such tweets and the users who post them and find that they have several distinguishing characteristics that sets them apart. We subsequently train a model for detecting such content and the users who post them.