Arabic Text Categorization Using Three Classifiers Methods: A Comparative Study

Today, text categorization is usually used in various areas, such
as: information retrieval, data mining and text mining. The
present study aims to test the K-Nearest Neighbors (KNN), Naïve
Bayes (NB), and Support Vector Machine (SVM) algorithms on
a relatively large dataset of Arabic documents. The latter dataset
includes 1,000 arabic documents that are distributed across 10
classes. The latter test is based on recall and precision measures.
It was found that Supporting Vector Machine algorithms
classifier outperforms the other ones.