Classification of News Articles for Learning Using the K-Nearest Neighbor Algorithm

Abstract

Tween Tribune is an online website that provides daily news articles for children, teenagers, and teachers. The purpose of this study is to classify articles based on the level of article popularity based on comments and the number of viewers available on Tween Tribune. The clustering of these categories is carried out using the k-Means Clustering method. The data classification process uses the k Nearest Neighbor algorithm. The classification results show that articles in the popular category contain the most commented and assigned data. Furthermore, it is shown by the reasonable result of the classification accuracy of 87.58%.