Prediction of COVID-19 Infection Based on Symptoms and Social Life Using Machine Learning Techniques
Stefanos Zervoudakis, Emmanouil Marakakis, Haridimos Kondylakis, Stefanos K. Goumas · 2021
COVID-19 pandemic has affected nearly every aspect of life. Observing online the spread of the virus can offer a complementary view to the cases that are daily officially recorded and reported. In this article, we present an approach that exploits information available on social media to predict whether a patient has been infected with COVID-19. Our approach is based on a Bayesian model that is trained using data collected online. Then the trained model can be used for evaluating the possibility that new patients are infected with COVID-19. The experimental evaluation presented shows the high quality of our approach. In addition, our model can be incrementally retrained, so that it becomes more robust in an efficient way.