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 discuss case studies of different perspectives through which we may detect and track online health misinformation, including rumors around Zika virus, the spread of unproven cancer treatment claims, and the anti-vaccination debate.
We will look at them through the lenses of machine learning for misinformation classification, cohort identification for user stance tracking, and network science for the quantification of the echo chamber effect. We will then discuss how these tools may fit into the larger battle against harmful information.