Date: 10/29/2019
Time: 1:00 pm - 2:00 pm
Location
Special Collections Seminar Room
Description
Abstract: Your mobile device knows a lot about you and that may be in your best interest. For the first time in human history a substantial portion of our daily behaviors are being recorded. While this presents legitimate concern for nefarious exploitation, with care taken for privacy, security and transparency, this abundance of personal data could also enable much more accurate and less obtrusive mental health assessment. Here, I will go over recent and on-going work toward AI-based language analyses that are beginning to provide powerful measurements of the mental health of people in their own words on social media. On the individual level, Facebook and Twitter have been found predictive of depression diagnoses, suicidality, cognitive impairment, personality, demographics, and occupational class (among others). At the community-level, Twitter has been found predictive of flu and allergy outbreaks, life satisfaction, atherosclerotic heart disease mortality, health behavioral risk factors, excessive drinking rates, and even real estate price changes. We are now working toward putting such techniques into action for better health care: detection of disease, differential diagnosis, personalizing treatment plans, monitoring progress, and ultimately saving lives.
Bio: Andrew Schwartz is an Assistant Professor of Computer Science at Stony Brook University (SUNY) and Director of the HLAB: Human Language Analysis Beings. His interdisciplinary research focuses on large and interpretable language analyses for health and psychological science. Utilizing natural language processing and machine learning techniques he seeks to discover new behavioral and psychological factors of health and well-being as manifest through language in social media. From 2012 to 2015, he was co-Founder and then Lead Research Scientist for the World Well-Being Project at the University of Pennsylvania, an interdisciplinary research team studying how big language analyses can reveal and predict differences in subjective well-being. He received his PhD in Computer Science from the University of Central Florida in 2011 with research on acquiring lexical semantic knowledge from the Web. His work has been widely featured in popular media including The New York Times, USA Today, and The Washington Post.
Registration
Bookings are closed for this event.
Clara Tran
Email: clara.tran@stonybrook.edu
Latest posts by Clara Tran (see all)
- Dr. Jesus Rios on “Can a machine learn chemistry?” - November 8, 2024
- Dr. Prerana Shrestha on “Engineering protein synthesis modulators to understand the neural basis of emotional behaviors” - October 7, 2024
- “Engineering Protein Synthesis Modulators to Understand the Neural Basis of Emotional Behaviors” on September 24 at 1pm - September 16, 2024
