Improving Arabic Sentiment Classification Using a Combined Approach

Belgacem Brahimi, Mohamed Touahria, Abdelkamel Tari


The aim of sentiment classification is to automatically extract and classify a textual review as expressing a positive or negative opinion. In this paper, we study the sentiment classification problem in the Arabic language. We propose a method that attempts to extract subjective parts of document reviews. In addition, a lexicon is used to find implicit opinions and sentiments in reviews. We combine the extracted opinions with the sentiment words returned by the lexical approach. Finally, a feature reduction technique is applied. To evaluate the proposed method, support vector machines (SVM) classifier is applied for the classification task. The results indicate that our proposed approach provides superior performance in terms of classification measures.


Text mining, opinion mining, sentiment classification, supervised learning, review extraction, combined approach

Full Text: PDF