Abstract
In this study flu trends identified from Twitter and official flu data from the Center for Disease Control and Prevention (CDC) for the state of Georgia were used to create machine learning models to predict flu outbreak. The quantitative study was performed using quasi-experimental design. Flu trends from CDC portal and tweets with mention of flu and influenza from the state of Georgia were used over the period of 22 weeks from December 29th, 2019 to May 30th, 2020 for this study. Performance of machine learning algorithms was measured and analyzed using statistical measures such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Square Error (MSE), Mean Absolute Percentage Error (MAPE), R-Squared, and adjusted R-Squared. Based on the results, the study found that there is an improvement in the performance of flu forecasting model based on machine learning algorithm when both official flu data from CDC and tweets with mention of flu are used.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
