Classification of Arabic News Texts with Fasttext Method

Access to information is getting easier day by day because of the entering our lives of the computer and especially the internet. As the internet access becomes easier and the internet users increase, the amount of data is growing every second. However, in order to access correct information, data must be classified. Classification is the process of separating data according to a certain semantic category. Dividing digital documents into semantic categories significantly affects the availability of the text. In this study, a text classification study was carried out on a data set obtained from different Arabic news sources. Firstly, the news texts were pre-processed and trunked. Pretreated texts were classified by K-Neighbors Classifier, Gaussian Naive Bayes, Multinomial Naive Bayes, Logistic Regression, Random Forest Classifier, Support Vector Classifier and Decision Tree Classifier methods after the FastText method was vectorized. According to the results of the study, the highest success rate was obtained by classification of the text obtained with the FastText vector model with approximately 90.36 % with Logistic Regression.