Last spring, GEOG researchers helped launch the UMD Global COVID Trends and Impact Survey (UMD-CTIS), a global Facebook survey to identify and track COVID-19 symptoms. In an article published yesterday by PNAS, the survey was found to give more accurate COVID-19 case count numbers than local government predictions in 77% of the 114 countries and territories included.
GEOG professor Kathleen Stewart and her team, along with the Joint Program in Survey Methodology (JPSM) and College of Information Studies, successfully trained a machine learning algorithm to identify which COVID-19 symptoms were most often associated with a positive result. They used that information, plus additional responses, to make close-to-reality predictions about case counts at that time.
“As the pandemic has evolved so has the survey—from variables looked at to questions asked,” said Stewart. “Very quickly after an individual completes the survey, we go through a set of processes to make that data available as quickly as possible. We offer data at both the regional and country level, and because it is a daily survey with machine learning models, local experts are able to take advantage of those granularities to support their decisions.”
Read more in the Maryland Today article written by Rachael Grahame. Illustration courtesy of iStock.