OUDJHANI, RadiaCHOUIT, Ikdam2024-03-312024-03-312023http://dspace.univ-skikda.dz:4000/handle/123456789/636Sentiment analysis is currently gaining significant attention in domains like politics, social sciences, marketing, and economics due to the influential role of opinions in decision- making processes. This study focuses on developing a sentiment analysis system specifically for Arabic texts. Unlike traditional approaches, we explore the potential of deep learning techniques, particularly BERT, in this field of automatic language processing. By leveraging BERT's advanced capabilities, we aim to enhance the accuracy and effectiveness of sentiment analysis in Arabic texts.enMaster 's degreed Diploma