Comparison of tuberculosis disease classification using support vector machine and Naive Bayes algorithm

Abstract

Tuberculosis (TB) is one of the biggest causes of death in the world. Some several symptoms and factors can be used to identify TB disease. One way that can be used is the classification method in data mining. This study compared the classification of TB disease using the Support Vector Machine (SVM) and Naive Bayes Algorithm. The research started by collecting data, then divided them into 13 independent variables and a dependent variable. After that, SVM and Naïve Bayes are implemented to classify the data. Based on the test results for each algorithm, with giving the amount of training data greater can give impact to the higher precision, recall, and accuracy values of the two algorithms used. In addition, for the case of Tuberculosis disease classification, the value of precision, recall, and accuracy in the Support Vector Machine algorithm is always higher than the Naive Bayes algorithm in all provided data.