Arabic Sentiment Analysis based Deep learning / Ikram Ouchen

Public ISBD Titre : Arabic Sentiment Analysis based Deep learning Type de document : document électronique Auteurs : Ikram Ouchen ; Anissa Aidi, Auteur ; Mediani,Chahrazed, Directeur de thèse Editeur : Setif:UFA Année de publication : 2025 Importance : 1 vol (86 f .) Format : 29 cm Langues : Anglais (eng) Catégories : Thèses & Mémoires:Informatique Mots-clés : Natural Language Processing (NLP) Deep Learning (DL) AraBERT Recurrent Neural Networks (RNN) Word2Vec TF-IDF Index. décimale : 004 Informatique Résumé : Arabic sentiment analysis is an offshoot of natural language processing (NLP) involved in classifying Arabic texts according to emotional content. Various factors hamper the successful attainment of high accuracy in sentiment classification of Arabic texts, such as rich morphology, different dialects, and poor availability of reliable annotated data. In this work, we address some of these issues by assessing and comparing different models dealing with Arabic sentiment analysis over the ar-reviews-100k dataset. Our approach involves classical models, deep learning models (LSTM, BiLSTM, GRU, and BiGRU), and transformer-based models, notably AraBERT. The experimental results show that deep learning models prove to be more competent than classical machine implementations. Considering these models, AraBERT outperformed the others in terms of accuracy, achieving a score of 74.5%. This indicates that transformer architectures could be strong candidates for Arabic sentiment analysis and potentially applicable in real-life situations, such as social media monitoring, customer feedback analysis, and market research. Note de contenu : Sommaire General Introduction…………………………………………………………………………….1 Chapter One: Literature Review…………………….………………………………………….3 Introduction.................................................................................................................... 4 Definitions ....................................................................................................................... 4 2.1.Sentiment Analysis .......................................................................................................... 4 2.2.Natural Language Processing (NLP) .................................................................................. 4 Data Utilized in Sentiment Analysis .................................................................................... 5 Characteristics .................................................................................................................. 5 4.1.Objectivity versus Subjectivity .......................................................................................... 5 4.2.Levels of Sentiment Analysis ............................................................................................. 6 Emotional Typologies in Sentiment Analysis ....................................................................... 6 Applications of Sentiment Analysis ..................................................................................... 7 Challenges Involved in Sentiment Analysis .......................................................................... 7 Techniques in Sentiment Analysis ....................................................................................... 8 Arabic Sentiment Analysis .................................................................................................. 9 9.1.Arabic language .............................................................................................................. 9 Conclusion ..................................................................................................................... 10 Chapter Two: AI & NLP……………………………………………………………………….12 Introduction................................................................................................................... 13 Machine Learning (ML) ................................................................................................... 13 Deep Learning (DL) ......................................................................................................... 14 3.1.Neural Networks (NN) .................................................................................................. 14 3.2.Core Architectures in Deep Learning ............................................................................... 15 3.3.Deep learning models ..................................................................................................... 15 4 Natural Language Processing (NLP) ................................................................................... 22 4.1.NLP fundamental subfields .............................................................................................. 22 4.2.NLP models .................................................................................................................. 24 Conclusion ..................................................................................................................... 31 Chapter Three: Related work & Methodology……………………………………………….33 Introduction................................................................................................................... 34 Related Work ................................................................................................................. 34 Methodology & Implementation ....................................................................................... 38 3.1.Data description ............................................................................................................. 38 3.2.Data collection............................................................................................................... 39 3.3.Data pre-processing ........................................................................................................ 40 3.4.Splitting datasets ............................................................................................................. 43 3.5.Vectorisation ................................................................................................................. 43 3.6.Model building .............................................................................................................. 45 3.7.Tools & libraries used ..................................................................................................... 54 Conclusion ..................................................................................................................... 58 Chapter Four: Evaluation & Results……………………………………………………….….58 Introduction................................................................................................................... 60 Performance metrics ........................................................................................................ 60 Experimental results ......................................................................................................... 62 3.1.Machine Learning models Results .................................................................................... 62 3.2.Deep Learning models Results ......................................................................................... 66 3.3.AraBERT ..................................................................................................................... 70 3.4.Models Performance Comparison .................................................................................... 73 3.5.Conclusion .................................................................................................................... 76 3.6.Graphical User Interface-Sentimento App ........................................................................ 77 General conclusion ........................................................................................................... 79 Bibliography .................................................................................................................... 81 Côte titre : MAI/1005 Arabic Sentiment Analysis based Deep learning [document électronique] / Ikram Ouchen ; Anissa Aidi, Auteur ; Mediani,Chahrazed, Directeur de thèse . - [S.l.] : Setif:UFA, 2025 . - 1 vol (86 f .) ; 29 cm. Langues : Anglais (eng) Catégories : Thèses & Mémoires:Informatique Mots-clés : Natural Language Processing (NLP) Deep Learning (DL) AraBERT Recurrent Neural Networks (RNN) Word2Vec TF-IDF Index. décimale : 004 Informatique Résumé : Arabic sentiment analysis is an offshoot of natural language processing (NLP) involved in classifying Arabic texts according to emotional content. Various factors hamper the successful attainment of high accuracy in sentiment classification of Arabic texts, such as rich morphology, different dialects, and poor availability of reliable annotated data. In this work, we address some of these issues by assessing and comparing different models dealing with Arabic sentiment analysis over the ar-reviews-100k dataset. Our approach involves classical models, deep learning models (LSTM, BiLSTM, GRU, and BiGRU), and transformer-based models, notably AraBERT. The experimental results show that deep learning models prove to be more competent than classical machine implementations. Considering these models, AraBERT outperformed the others in terms of accuracy, achieving a score of 74.5%. This indicates that transformer architectures could be strong candidates for Arabic sentiment analysis and potentially applicable in real-life situations, such as social media monitoring, customer feedback analysis, and market research. Note de contenu : Sommaire General Introduction…………………………………………………………………………….1 Chapter One: Literature Review…………………….………………………………………….3 Introduction.................................................................................................................... 4 Definitions ....................................................................................................................... 4 2.1.Sentiment Analysis .......................................................................................................... 4 2.2.Natural Language Processing (NLP) .................................................................................. 4 Data Utilized in Sentiment Analysis .................................................................................... 5 Characteristics .................................................................................................................. 5 4.1.Objectivity versus Subjectivity .......................................................................................... 5 4.2.Levels of Sentiment Analysis ............................................................................................. 6 Emotional Typologies in Sentiment Analysis ....................................................................... 6 Applications of Sentiment Analysis ..................................................................................... 7 Challenges Involved in Sentiment Analysis .......................................................................... 7 Techniques in Sentiment Analysis ....................................................................................... 8 Arabic Sentiment Analysis .................................................................................................. 9 9.1.Arabic language .............................................................................................................. 9 Conclusion ..................................................................................................................... 10 Chapter Two: AI & NLP……………………………………………………………………….12 Introduction................................................................................................................... 13 Machine Learning (ML) ................................................................................................... 13 Deep Learning (DL) ......................................................................................................... 14 3.1.Neural Networks (NN) .................................................................................................. 14 3.2.Core Architectures in Deep Learning ............................................................................... 15 3.3.Deep learning models ..................................................................................................... 15 4 Natural Language Processing (NLP) ................................................................................... 22 4.1.NLP fundamental subfields .............................................................................................. 22 4.2.NLP models .................................................................................................................. 24 Conclusion ..................................................................................................................... 31 Chapter Three: Related work & Methodology……………………………………………….33 Introduction................................................................................................................... 34 Related Work ................................................................................................................. 34 Methodology & Implementation ....................................................................................... 38 3.1.Data description ............................................................................................................. 38 3.2.Data collection............................................................................................................... 39 3.3.Data pre-processing ........................................................................................................ 40 3.4.Splitting datasets ............................................................................................................. 43 3.5.Vectorisation ................................................................................................................. 43 3.6.Model building .............................................................................................................. 45 3.7.Tools & libraries used ..................................................................................................... 54 Conclusion ..................................................................................................................... 58 Chapter Four: Evaluation & Results……………………………………………………….….58 Introduction................................................................................................................... 60 Performance metrics ........................................................................................................ 60 Experimental results ......................................................................................................... 62 3.1.Machine Learning models Results .................................................................................... 62 3.2.Deep Learning models Results ......................................................................................... 66 3.3.AraBERT ..................................................................................................................... 70 3.4.Models Performance Comparison .................................................................................... 73 3.5.Conclusion .................................................................................................................... 76 3.6.Graphical User Interface-Sentimento App ........................................................................ 77 General conclusion ........................................................................................................... 79 Bibliography .................................................................................................................... 81 Côte titre : MAI/1005

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
MAI/1005	MAI/1005	Mémoire	Bibliothèque des sciences	Anglais	Disponible Disponible

---

1 (1 - 1 / 1)