<![CDATA[Automated document classification is becoming important and highly required for many applications, particularly in light of the exponential increase of Arabic-language internet documents. Text classification is a big data issue and an essential aspect of our lives; classifying content in a typical Arabic text is a significant and arduous challenge. The process of classifying a document involves placing it in the appropriate class or category. The major goal of this work is to use pre-processing techniques to evaluate the effectiveness of machine learning (ML) algorithms. The inclusion of preprocessing in this research methodology is vital. This study uses machine learning methods to classify different Arabic documents and uses five well-known classification systems' performance in categorizing the documents. This work used a model developed using various algorithms, namely Support Vector Machines, Naive Bayes, Logistic Regression, K-Nearest Neighbors, and Random Forest, for the classification procedures. The findings indicate that SVM achieved the highest performance evaluation, boasting an accuracy of 98%, surpassing all other algorithms employed in this study.]]>
Copyrights © 2025
