Sentiment analysis involves using computational methods to identify and classify opinions expressed in text, with the goal of determining whether the writer's stance towards a particular topic, product, or idea is positive, negative, or neutral. However, sentiment analysis in Arabic presents unique challenges due to the complexity of Arabic morphology and the variety of dialects, which make language classification even more difficult. To address these challenges, we conducted to investigation and overview the techniques used in the last five years for embedding and classification of Arabic sentiment analysis (ASA). We collected data from 100 publications, resulting in a representative dataset of 2,300 detailed records that included attributes related to the dataset, feature extraction, approach, parameters, and performance measures. Our study aimed to identify the most powerful approaches and best model settings by analyzing the collected data to identify the significant parameters influencing performance. The results showed that Deep Learning and Machine Learning were the most commonly used techniques, followed by lexicon and transformer-based techniques. However, Deep Learning models were found to be more accurate for sentiment classification than other Machine Learning models. Furthermore, multi-level embedding was found to be a significant step in improving model accuracy.
Despite the high performance of the existing embedding approaches for Aspect-Based Sentiment Analysis (ABSA), such as Word2Vec and GloVe, they still have several limitations, mainly in contextual understanding and relational insights of natural language, especially in complex and long sentences. This paper presents a novel approach that enhances ABSA by integrating knowledge graphs into a transformer model, where the graphs are automatically built from raw text without requiring external resources, making the system adaptable and fully data-driven. Our approach allows a better understanding of context and relationships between entities, by combining of the contextual understanding of BERT with the relational insights provided by Node2Vec, a graph-based embedding technique. In this paper, we benchmark our hybrid embedding technique with the existing state-of-the-art embedding techniques. Specifically, we compare traditional embeddings, such as Word2Vec and GloVe, against BERT for textual input, while also exploring Word2Vec and Node2Vec for graph-based embeddings. Our experiments demonstrate that combining BERT’s deep contextual embeddings with the structural insights of Node2Vec leads to promising improvements in sentiment classification performance. Our model achieved 98% accuracy on SemEval2015 Restaurant dataset. These results demonstrate that integrating both contextual and relational information significantly enhances the performance of ABSA models, thereby making them more effective at capturing nuanced sentiment relationships. The proposed model’s modular design also allows flexible integration of alternative embeddings or graph configurations, making it suitable for broader sentiment analysis applications beyond the benchmark datasets.