A Novel Text Classification Technique Using Improved Particle Swarm Optimization: A Case Study of Arabic Language

We propose a novel text classification model, which aims to improve the performance of Arabic using machine learning techniques. One effective solutions in is find suitable feature selection method with an optimal number features alongside classifier. Although several methods have been proposed for language different techniques, such as methods, ensemble classifiers, and discriminative features, choosing becomes NP-hard problem considering huge search space. Therefore, we method, called Optimal Configuration Determination Classification (OCATC), utilized Particle Swarm Optimization (PSO) algorithm solution (configuration) from this The OCATC extracts converts textual documents into numerical vector Term Frequency-Inverse Document Frequency (TF–IDF) approach. Finally, PSO selects best architecture set classifiers features. Extensive experiments were carried out evaluate six datasets, including five publicly available datasets our dataset. results obtained demonstrate superiority over individual other state-of-the-art methods.