Yelena Mejova, Capturing Social Media Signals for Epidemiology & Health Misinformation

Dates: 
Wednesday, February 10, 2021 - 11:00am to 12:05pm
Location: 
Zoom - contact events@cs.stonybrook.edu for Zoom info.
Event Description: 

Abstract: The scale and complexity of human behavior traces captured on the web have revolutionized disease tracking, pushing the lag of conventional health surveillance to more real-time "now-casting". These signals also provide a rich tableau of the context around people's health conditions, as well as cultural, social, and personal attitudes which affect their behavior and health-related beliefs. In this talk, I will provide case studies in using computational tools to extract signals from Facebook, Twitter, Google, and other popular internet platforms that allow health surveillance, as well as public opinion monitoring around disease. Using a combination of natural language processing, machine learning, and network analysis methods I will illustrate the benefits and many limitations of social media data. These methods span text mining of tweets and domain adaptation of models, partitioning of communication networks to find echo-chambers, monitoring search engine result coverage and data stability, and detecting change points in media sharing behavior as a proxy of mobility. Further, I will put social media platforms in context of political and social forces that shape the information available to its users, and propose methods for health misinformation tracking across topics spanning cancer, infectious and non-communicable diseases, vaccination, and specifically around COVID-19.

Title: Capturing Social Media Signals for Epidemiology & Health Misinformation

Bio: Yelena Mejova is a Senior Research Scientist at the ISI Foundation in Turin, Italy, a part of the Data Science for Social Impact and Sustainability group. Specializing in social media analysis and mining, her work concerns the quantification of health and wellbeing signals in social media, as well as tracking of social phenomena, including politics and news consumption. Her work on modeling exercise using technology and personal moral values won a Best Paper Award at the ACM Conference on User Modeling, Adaptation and Personalization (UMAP) in 2019. She has co-organized the ACM Conference on Digital Health, as well as numerous workshops around data science for health and vulnerable populations. Previously, as a scientist at the Qatar Computing Research Institute, Dr. Mejova specialized in tracking non-communicable diseases at the Social Computing group. She has received a Ph.D. in Computer Science at the University of Iowa, and as a postdoctoral researcher at Yahoo! Research Barcelona was a part of the Web Mining and User Experience groups.

Hosted By: 
Klaus Mueller
Computed Event Type: 
Mis