Text classification is an important task which may help human reducing time and effort. This work is aimed to propose an approach for text classification, especially for articles. The proposed method can automatically extract information and categorize articles on suitable topics. The input data were pre-processed, extracted, vectorized and classified using machine learning techniques including Support Vector Machines, Naïve Bayes, and k-Nearest Neighbors. The experiments were carried out on two data sets of articles showed that with the accuracy of over 91%, using natural language processing and support vector machines technique proved its feasibility for developing the automatic classification system of articles.