Despite increased advancements of medical technology and availability of vaccines, emerging and re-emerging epidemics such as SARS, influenza A(H1N1), avian flu, Ebola and Zika, continue to pose tremendous threats. Early detection and immediate response are essential to avoid the repercussions of an epidemic. However, in many cases current methods and algorithms for epidemic detection are no longer able to keep up with the new demands. The availability of unprecedented amount of social media data has provided an opportunity to develop new surveillance systems. In this project we propose a novel integrated framework of network theory, data mining and partial differential equation for early detection of epidemic outbreaks based on real-time Geo-tagged data in Twitter. The project develops new algorithms of community detection and topic analysis of Geo-tagged data in Twitter, new effective distance metric for epidemic spreading and new mathematical theorems for faster, near real-time, and localized detection of epidemic outbreaks. This project is funded by NSF.
This website showcases research results and the visualization of the output of the Real-Time Twitter-based Flu Surveillance System.