Analyse des sentiments Appliquée aux dialectes arabes

Abstract

Sentiment analysis, also known as Opinion Mining, is a subfield of natural language processing. Since humans are omnipresent in today’s ultra-connected world thanks to social networks, they are constantly expressing their opinions on multiple topics in a multitude of occasions. Sentiment analysis is therefore crucial to identify the user’s opinion and interests. When the user is native of the Arabic world, things are not different, on the contrary, the richness and diversity of Arabic dialects makes social networks full of opinions. It is therefore wise to try to exploit this mass of information to extract useful information. In this work, we focus on the sentiment analysis of Arabic dialects (focal point on the Algerian dialect), in order to make a state of the art inventory of the different approaches and techniques used