Enhancing the Performance of Sentiment Analysis Supervised Learning Using Sentiments Keywords Based Technique

Sentiment Analysis (SA) and machine learning techniques are collaborating to understand the attitude of text writer, implied in particular text. Although, SA is an important challenging itself, it is very important challenging in Arabic language. In this paper, we are enhancing sentiment analysis in Arabic language. Our approach had begun with special pre-processing steps. Then, we had adopted sentiment keywords co-occurrence measure (SKCM), as an algorithm extracted sentiment-based feature selection method. This feature selection method had utilized on three sentiment corpora using SVM classifier. We compared our approach with some traditional methods, followed by most SA works. The experimental results were very promising for enhancing SA accuracy.