부산대학교 도서관

Much news is available online, and not all is categorized. A few researchers have carried out work on news classification in the past, and most of the work focused on fake news identification. Most of the work performed on news categorization is carried out on a benchmark dataset. The problem with the benchmark dataset is that model trained with it is not applicable in the real world as the data are pre-organized. This study used machine learning (ML) techniques to categorize online news articles as these techniques are cheaper in terms of computational needs and are less complex. This study proposed the hyperparameter-optimized support vector machines (SVM) to categorize news articles according to their respective category. Additionally, five other ML techniques, Stochastic Gradient Descent (SGD), Random Forest (RF), Logistic Regression (LR), K-Nearest Neighbor (KNN), and Naïve Bayes (NB), were optimized for comparison for the news categorization task. The results showed that the optimized SVM model performed better than other models, while without optimization, its performance was worse than other ML models.