COVID-19 Prediction Applying Supervised Machine Learning Algorithms with Comparative Analysis Using WEKA

Early diagnosis is crucial to prevent the development of a disease that may cause danger human lives. COVID-19, which contagious has mutated into several variants, become global pandemic demands be diagnosed as soon possible. With use technology, available information concerning COVID-19 increases each day, and extracting useful from massive data can done through mining. In this study, authors utilized supervised machine learning algorithms in building model analyze predict presence using Symptoms Presence dataset Kaggle. J48 Decision Tree, Random Forest, Support Vector Machine, K-Nearest Neighbors Naïve Bayes were applied WEKA software. Each model’s performance was evaluated 10-fold cross validation compared according major accuracy measures, correctly or incorrectly classified instances, kappa, mean absolute error, time taken build model. The results show Machine Pearson VII universal kernel outweighs other by attaining 98.81% error 0.012.