KLASIFIKASI SPAM SMS MENGGUNAKAN NAÏVE BAYES CLASSIFIER DAN K-NEAREST NEIGHBOR

Adnan Sauddin
Try Azisah Nurman
Nur Aeni
Sadem Rahayu Sudarta

Jurnal Matematika dan Statistika serta Aplikasinya (Jurnal MSA)
Vol 13 No 1 (2025): VOLUME 13 NO 1 TAHUN 2025

This research discusses the classification of the SMS Spam dataset. Indonesia is in 19th position for the most SMS spam in the world. Many fraudulent crimes that cause losses to users come from SMS spam. SMS spam classification can be done using machine learning methods, namely Naïve Bayes Classifier (NBC) and K-Nearest Neighbor (KNN) using term frequency word weighting. This research aims to determine the performance of SMS spam classification using the NBC algorithm and the KNN algorithm. This research shows that the classification accuracy using the Naïve Bayes Classifier method is greater, namely 98.3% compared to the K-Nearest Neighbor method with an accuracy of 95.1% with an accuracy ratio of 1.033, which shows that the Naïve Bayes Classifier method has better performance.