MARC details
| 000 -LEADER |
|---|
| fixed length control field |
06322nam a22002657a 4500 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION |
|---|
| fixed length control field |
201210b2025 a|||f bm|| 00| 0 eng d |
| 024 7# - Author Identifier |
|---|
| Standard number or code |
0000-0001-7713-9682 |
| Source of number or code |
ORCID |
| 040 ## - CATALOGING SOURCE |
|---|
| Original cataloging agency |
EG-CaNU |
| Transcribing agency |
EG-CaNU |
| 041 0# - Language Code |
|---|
| Language code of text |
eng |
| Language code of abstract |
eng |
| -- |
ara |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER |
|---|
| Classification number |
610 |
| 100 0# - MAIN ENTRY--PERSONAL NAME |
|---|
| Personal name |
Yomna Eid Mohamed Rizk |
| 245 1# - TITLE STATEMENT |
|---|
| Title |
Multi-Domain Aspect-Based Sentiment Analysis Using Transformer-Based Models On Arabic Corpus |
| Statement of responsibility, etc. |
/Yomna Eid Mohamed Rizk |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. |
|---|
| Date of publication, distribution, etc. |
2025 |
| 300 ## - PHYSICAL DESCRIPTION |
|---|
| Extent |
p. |
| Other physical details |
ill. |
| Dimensions |
21 cm. |
| 500 ## - GENERAL NOTE |
|---|
| Materials specified |
Supervisor: Walaa Medhat |
| 502 ## - Dissertation Note |
|---|
| Dissertation type |
Thesis (M.A.)—Nile University, Egypt, 2025 . |
| 504 ## - Bibliography |
|---|
| Bibliography |
"Includes bibliographical references" |
| 505 0# - Contents |
|---|
| Formatted contents note |
Contents:<br/>Contents<br/>Page<br/>CERTIFICATION OF APPROVAL ii<br/>COPYRIGHT iii<br/>ACKNOWLEDGEMENTS iv<br/>ABSTRACT v<br/>Dedication . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . vi<br/>LIST OF FIGURES xi<br/>LIST OF TABLES xii<br/>LIST OF EQUATIONS xiii<br/>Chapters:<br/>1. Introduction 1<br/>1.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1<br/>1.2 Problem Statement . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2<br/>1.3 Thesis Contributions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3<br/>1.4 Organization of the Thesis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4<br/>2. Background and Concepts 5<br/>2.1 Sentiment Analysis (SA) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5<br/>2.2 Aspect-Based Sentiment Analysis (ABSA) Task . . . . . . . . . . . . . . . . . . . . . 6<br/>2.2.1 ABSA in the Arabic Language . . . . . . . . . . . . . . . . . . . . . . . . . . . 7<br/>vii<br/>2.2.2 Models for ABSA . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8<br/>2.3 Multi-domain ABSA . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13<br/>3. Background and Literature Review 15<br/>3.1 Existing ABSA Models in English . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15<br/>3.2 Arabic Single-Domain ABSA Datasets . . . . . . . . . . . . . . . . . . . . . . . . . . 19<br/>3.3 Arabic Single-Domain ABSA Models . . . . . . . . . . . . . . . . . . . . . . . . . . . 20<br/>3.4 Multi-domain ABSA . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22<br/>3.4.1 Methodologies of Multi-Domain ABSA . . . . . . . . . . . . . . . . . . . . . . 23<br/>3.4.2 Models for Multi-Domain ABSA . . . . . . . . . . . . . . . . . . . . . . . . . . 23<br/>4. Multi-Domain Aspect-Based Sentiment Analysis Proposed Model 26<br/>4.1 A-MASA: Arabic Multi-Domain Aspect-Based Sentiment Analysis Datasets . . . . . . 27<br/>4.1.1 Dataset Construction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27<br/>4.1.2 Dataset Cleaning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31<br/>4.1.3 Dataset Annotation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32<br/>4.1.4 Dataset Preparation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33<br/>4.2 ABSA Models . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35<br/>5. Experimental Evaluation 40<br/>5.1 Experimental Setup . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40<br/>5.2 A-MASA Evaluation Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 43<br/>5.3 Muli-Domain ABSA Models Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45<br/>5.3.1 Muli-Domain Aspects Extraction Results . . . . . . . . . . . . . . . . . . . . . 45<br/>5.3.2 Muli-Domain Aspects Sentiment Classification Results . . . . . . . . . . . . . 48<br/>5.4 Other Models Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 49<br/>5.4.1 Comparison Between Our Model and Arabic Single-domain AE Model . . . . . 49<br/>5.4.2 Comparison Between Multi-domain Arabic ABSA Model and LLMs-based Models . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 50<br/>6. Conclusions and Future Work 52<br/>viii<br/>6.1 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 52<br/>6.2 Future Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 53<br/>Bibliography 60<br/>Appendices:<br/>A. Publications |
| 520 3# - Abstract |
|---|
| Abstract |
Abstract:<br/>Aspect-Based Sentiment Analysis (ABSA) is a fine-grained Sentiment Analysis (SA) task that<br/>identifies sentiments expressed towards specific aspects within a sentence. Despite the increasing use<br/>of Semitic languages like Arabic in Natural Language Processing (NLP), there remains a scarcity of<br/>resources and datasets for Arabic ABSA. To address these challenges, we introduce a new manually<br/>annotated multi-domain dataset, A-MASA (Arabic Multi-domain Aspect-based Sentiment Analysis), comprising 6,500 records from different domains and dialects. Additionally, a generalized model<br/>for Arabic multi-domain ABSA was developed and trained on both A-MASA and existing datasets,<br/>covering a total of nine domains. The proposed model integrates three state-of-the-art pre-trained<br/>models, each fine-tuned with additional layers, and combines their outputs using a weighted sum ensemble technique. Comprehensive experiments were conducted to evaluate the model’s performance.<br/>For the Aspect Extraction (AE) task, the QARiB model achieved the highest F1-score of 88.7% on<br/>the hotels domain, while the ensemble model reached the highest F1-score of 88.9% on the products<br/>domain. For aspect sentiment classification, the ensemble model recorded an F1-score of 87.5% on<br/>the hotels domain. The ensemble model demonstrated superior generalization, outperforming existing single-domain models on unseen data, achieving 37% improvement in the books domain and<br/>14% in the hotels domain for the AE task. Additionally, the model surpassed two Large Language<br/>Models (LLMs), achieving an F1-score of 88.9% in the products domain 49% higher than JAIS and<br/>31% higher than Gemini.<br/>keywords<br/>Arabic Aspect-Based Sentiment Analysis (ABSA), Multi-domain Sentiment Analysis, Natural Language Processing (NLP), Ensemble Learning Models, Arabic Datasets. |
| 546 ## - Language Note |
|---|
| Language Note |
Text in English, abstracts in English and Arabic |
| 650 #4 - Subject |
|---|
| Subject |
InformaticsIFM |
| 655 #7 - Index Term-Genre/Form |
|---|
| Source of term |
NULIB |
| focus term |
Dissertation, Academic |
| 690 ## - Subject |
|---|
| School |
InformaticsIFM |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) |
|---|
| Source of classification or shelving scheme |
Dewey Decimal Classification |
| Koha item type |
Thesis |
| 655 #7 - Index Term-Genre/Form |
|---|
| -- |
187 |