Sentiment Classification at the Time of the Tunisian Uprising: Machine Learning Techniques Applied to a New Corpus for Arabic Language

Sentiment analysis is the field of study that analyzes people´s opinions, sentiments, attitudes, and emotions from written language. It is one of the most active research areas in natural language processing and is also widely studied in data mining, web mining, and text mining. In recent years, text mining and sentiment analysis are being in almost every business and social domain which study all human activities and key influencers of our behaviors. Even though there are, at present, several studies related to this theme, most of them focus mainly on English texts. The resources available for opinion mining in other languages, such as Arabic, are still limited. In this paper, we propose a new sentiment analysis system destined to classify users´ opinions which is performed with a new corpus for Arabic language gathered from users´ posts at the time of the Tunisian revolution. Furthermore, different experiments have been carried out on this corpus, using machine learning algorithms such as Support Vector Machines and Naïve Bayes.