Abstract—This paper introduces a novel approach for automated negation detection in Arabic reviews, leveraging advanced supervised classification techniques. We explore various methods, including naïve bayes (kernel), decision tree, and k-nearest neighbors, to analyze lexical and structural features from an Arabic text corpus. Our experimental results reveal that the decision tree model achieves the highest accuracy at 97.13%, significantly outperforming other classifiers. This advancement highlights the effectiveness of our approach in enhancing sentiment analysis for Arabic text, demonstrating a major improvement in negation detection capabilities.
 
Keywords—Arabic sentiment analysis, machine learning, natural language processing, negation detection, supervised classification


Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).