Project Title: “Georgia Scope”: an enabling infrastructure for disease surveillance in Georgia
Principal Investigator: Dr. Chun Hai (Isaac) Fung (College of Public Health)
Co-Investigator: Dr. Tsz ho “Zion” Tse (College of Engineering, University of Georgia)
We intend to build a critical health information infrastructure, namely “Georgia Scope,” in a comprehensive channel of website and database for real-time public health surveillance and health communication evaluation in Georgia. Rural Georgia is an economically underdeveloped area with an unemployment rate higher than the national average and a poor public transportation network, where resources for real-time epidemic monitoring and effective public health surveillance are less focused and the coverage of healthcare providers and health insurance is less than ideal. We propose to improve public health surveillance in Georgia by analyzing health-related keywords in tweets by more than two million local Twitter users and comparing it with data released from the Georgia Department of Public Health (DPH). While social media has been shown as a powerful tool for tracking public dynamics and patterns, “Georgia Scope” will be the first digital infrastructure for real-time disease monitoring in Georgia. The analyzed results will be made public 24/7/365 on the “Georgia Scope” website for sharing with a diverse audience including residents and travelers in Georgia, local health departments, and public health researchers. Aim #1: We will create a data streaming interface with Twitter and collect baseline information (counties, tweets) of the population in Georgia. We will first build and host the supporting cyber structure and servers, using the resources from the Georgia Advanced Computing Research Center (GACRC) at the University of Georgia, for continuously acquiring data (100Gbps) from the Twitter Application Programming Interface (API). The acquired Twitter information, including user names and IP addresses, will be made anonymous and stored in the secured GACRC cloud computing facility. Aim #2: We will report and analyze Twitter traffic data with keywords specific to various diseases and health conditions, as well as the self-reported and estimated geographical location of the Twitter users, in order to obtain the database of these tweets in Georgia and its subdivisions (counties or health districts). Our computer infrastructure (Aim #1) will be applied for disease surveillance and outbreak detection by analyzing and developing a statistical correlation between (1) Twitter traffic volume of keywords for diseases in time series and (2) Georgia DPH incidence data of such diseases in Georgia and its subdivisions. Aim #3: We will create the “Georgia Scope” website hosted at GACRC to store and make our Twitter data and analysis publicly available online. Through an automated process, “Georgia Scope” will be updated 24/7/365 for public health data, serving as the hub for sharing with a diverse audience of any individuals and health departments.
Last updated: 9/26/2014