I am a researcher at the University of Pennsylvania. My current appointment is with the Department of Biostatistics, Epidemiology and Informatics (DBEI) at the Perelman School of Medicine (PSOM).  I am a senior member of the Health Language Processing Lab (HLP), which is part of the Institute of Biomedical Informatics.

My research interests include natural language processing (NLP), social media mining (SMM), applied machine learning (ML) and biomedical informatics. I am the Principal Investigator (PI) of the NIDA-NIH funded grant titled: Mining Social Media Big Data for Toxicovigilance: Automating the Monitoring of Prescription Medication Abuse via NLP and ML Methods (R01DA046619). The goal is to develop methods that can effectively utilize the vast amounts of data about prescription medication abuse, including opioid abuse, that is publicly available via social media to better understand and characterize the problem. Funding for the project started on July 1, 2018, so stay tuned for more details.

I am also interested in topics such as drug safety, mental health, evidence-based medicine, and health-related communication via social media.

I believe in reproducible and community-driven research, and always try to publicly publish my code (e.g., here and here) and data (e.g., here and here).

I teach professionally and as a hobby. I frequently run specialized workshops on NLP, SMM and applied ML to teach/train researchers and students from a wide spectrum of educational backgrounds.

I am available (and typically enthusiastic) to work on new, challenging projects, run specialized workshops, or talk about potential applications of NLP and applied ML using big and small data. Feel free to contact me via email.