February 13, 2020
12:00 PM - 1:30 PM
Title: Understanding Health Behaviors Using Social Media Language Data
Abstract: The language people use on social media provides a rich and imperfect portal into who they are, revealing psychological traits and drivers of mental and physical well-being. We show how models built on tens of millions of Facebook posts can help diagnose and understand depression and how the language in billions of tweets compared to county level health data suggest potential psychological risk factors for heart disease. Social media language also reveals a host of psychological risk factors such as stress and loneliness.
Bio: Lyle Ungar is a Professor of Computer and Information Science at the University of Pennsylvania, where he also holds appointments in multiple departments in the Schools of Business, Medicine, Arts and Sciences, and Engineering and Applied Science. He has published over 300 articles, supervised two dozen Ph.D. students, and is co-inventor on ten patents. His current research focuses on developing scalable machine learning methods for data mining and text mining, including deep learning methods for natural language processing and analysis of cell phone and social media to better understand the drivers of physical and mental well-being.