A CyberGIS-enabled Pandemic Warning System Using Social Media Data

Keywords: CyberGIS, Human mobility, Time Series Forecasting
Session Type: Virtual Paper Abstract
Day: Sunday
Session Start / End Time: 2/27/2022 05:20 PM (Eastern Time (US & Canada)) - 2/27/2022 06:40 PM (Eastern Time (US & Canada))
Room: Virtual 63

Abstract

Human mobility plays a vital role in the spread of respiratory infectious diseases such as COVID-19. It is essential for first responders and policy-makers to take human mobility patterns into account for making decisions against pandemics such as COVID-19. Existing COVID-19 assessment studies have developed time series forecasting models or risk indicators using infection, death, and recovery data or socio-economic data like racial, ethnic, and household income. However, the amount and complexity of geospatial data make it difficult for non-experts to include human mobility analysis into decision support tools where a model for time series forecasting or risk assessment can run in an interactive fashion. To fill this gap, we have developed a CyberGIS-enabled pandemic warning system where users can (1) run time-series analysis and forecasting models of COVID-19 risk by region, and (2) create multiple linked views illustrating COVID-19 risk based on human mobility patterns derived from Twitter data. The system is designed to support policymakers to identify places with a higher risk of outbreaks and to prioritize life-saving resources for the most efficient interventions. Moreover, by utilizing cutting-edge CyberGIS capabilities, we anticipate that decision-makers would have easy access to the visualization of regional COVID-19 risk based on human mobility patterns. Finally, the system can be applied to other infectious diseases in which human mobility affects the spread of disease.