Word Clustering as a Feature for Arabic Sentiment Classification

Rich morphology language, such as Arabic, requires more investigation and methods targeted toward improving the sentiment analysis task. An example of external knowledge that may provide some semantic relationships within the text is the word clustering technique. This article demonstrates the ongoing work that utilizes word clustering when conducting Arabic sentiment analysis. Our proposed method employs supervised sentiment classification by enriching the feature space model with word cluster information. In addition, the experiments and evaluations that were conducted in this study demonstrated that by combining the clustering feature with sentiment analysis for Arabic, this improved the performance of the classifier.