A Proposed Lexicon-Based Sentiment Analysis Approach for the Vernacular Algerian Arabic M’hamed Mataoui, 1 Omar Zelmati, 2 Madiha Boumechache 2 1 IS&DB laboratory, Ecole Militaire Polytechnique, Algiers, Algeria 2 Ecole Militaire Polytechnique, Algiers, Algeria mataoui.mhamed@gmail.com, omar.zelmati@gmail.com, madiha.boumechache@gmail.com Abstract. Nowadays, sentiment analysis research is widely applied in a variety of applications such as marketing and politics. Several studies on the Arabic sentiment analysis have been carried out in recent years. These studies mainly focus on Modern Standard Arabic among which few studies have investigated the case of Arab dialects, in this case, Egyptian, Jordanian, and Khaliji. In this paper, we propose a new lexicon-based sentiment analysis approach to address the specific aspects of the vernacular Algerian Arabic fully utilized in social networks. A manually annotated dataset and three Algerian Arabic lexicons have been created to explore the different phases of our approach. Keywords: Arabic sentiment analysis, vernacular Algerian Arabic, Algerian dialect, Modern Standard Arabic, Social networks. 1 Introduction The last years are mainly characterized by the fast proliferation of social networking services such as Facebook, Twitter and YouTube. These social networks allowed individuals and groups to express and share their opinions about different kinds of topics (products, political events, economics, restaurants, books, hotels, video clips, etc.). Billions of comments and reviews are added to the web each day, which has led to the need to mine users’ opinions in order to discover useful information. Mining this enormous volume of comments and reviews is almost impossible manually. Therefore, a new thematic of Natural Language Processing (NLP), known as senti- ment analysis (SA) or opinion mining (OM), emerged. The main purpose of sentiment analysis is to extract users’ sentiments/opinions from created contents by using auto- matic mining techniques to determine their attitudes with respect to some topic, often expressed in textual form. Nowadays, sentiment analysis is used mainly by businesses to discover the opin- ions of different customers as part of marketing purposes [1, 2]. It is also used in poli- tics to predict election results or to know public opinions about different policies. SA field is considered as a classification task for deciding about an opinion as being posi- tive, negative, or neutral. 55 Research in Computing Science 110 (2016) pp. 55–70; rec. 2016-02-07; acc. 2016-03-06