Currently short messages or known as SMS (short message service) is one of the communication media that is often used by some irresponsible people to commit criminal acts of fraud. This type of SMS that is abused is called spam. To overcome this problem, SMS operators need to filter the type of incoming SMS to clients using a classification algorithm. One of the classification methods that can be used is the Naïve Bayes method. The Naïve Bayes method is a classification method in machine learning that involves the concept of probability. This method is a simple Bayes algorithm model and it can be used to classify text or document data. In this paper the Naïve Bayes method is applied for SMS data classification analysis. This method is used to classify the type of SMS whether it is "spam" or not spam (called "ham"). Based on the results of the analysis by trying several proportions of the distribution of training data and testing data, the best accuracy results were obtained at 97% using a training-testing data ratio of 60: 40.
Copyrights © 2023