The effects of Pre-Processing Techniques on Arabic Text Classification

In the last two decades, the amount of available Arabic text data on the World Wide Web is dramatically growing, making it the fourth most used language on the web. Accordingly, the demand for efficient Arabic text classification is increasing, especially for web page content filtering, information retrieval, and e-mail spam detection. Several Machine Learning algorithms have been implemented to classify Arabic documents. However, the results achieved are not comparable with those obtained in other languages such as English, primarily when using preprocessing techniques that do not take into consideration the Arabic language features. This paper investigates the impact of wisely selected preprocessing techniques on the efficiency of different text classification algorithms. The effects of stop words removal, stemming, lemmatization, and all possible combinations are examined. The reported results (+10.75% to +28.73%) prove the effectiveness of using these techniques either individually or in combination.