Application of Naïve Bayes Algorithm on Determining Student Concentration in Mathematics Learning Process

This research on student concentration in the math learning process by applying the Naïve Bayes algorithm which aims to (1) determine the Naïve Bayes Algorithm in determining student concentration in the math learning process, (2) determine the chances of student concentration in the math learning process. This research uses the Naïve Bayes classification data mining method. This research was conducted at SMPN 4 Cirebon City with a total sample of 101 students The instrument used was a student questionnaire. The results showed: data mining has 4 stages consisting of datasets, data cleaning, data grouping, namely data grouping, and Naïve Bayes algorithm modeling. A model was obtained to predict the class by multiplying the probability of each criterion and then multiplying it by the probability of concentration or the probability of less concentration. There are 0.7 concentration classes and 0.3 less concentration classes. Based on the RapidMiner application, there is an Accuracy value of 94.00%. Class precision on concentration prediction has a value of 94.44%, while the prediction of less concentration has a value of 92.85%. Class recall on true concentration has a value of 97.14%, while on true lack of concentration has a value of 85.57%.