Mining Potentially Unreported Effects from Twitter Posts through Relational Similarity - A Case for Opioids.

Growing uses of opioids for pain management have led to a crisis of addiction and thousands of deaths in the United States. Although many of the opioid effects have been observed and reported, experience directly from the opioid users may help provide additional information in identifying any potentially unreported effects. In this study, we developed a neural embedding-based method to discover potential opioid-effect relations through similar relations of known medication effects. Using a corpus of 3.6 million clean unannotated tweets, a vector space model was learned with word2vec, and the model was used to identify potential opioid effects. The inferred results were further verified against 5 authoritative sources of medication effects. Seven of inferred effects were identified as potentially unreported, demonstrating the power and utility of our method. It is conceivable that our approach can be applied to discovery of potentially unreported effects of other medications.