article · Electronics
Aspect-based sentiment analysis identifies specific subjects discussed within text and determines the sentiment expressed towards each one. While transfer learning is widely used for language processing tasks, its application to aspect term extraction and aspect polarity detection in Arabic text has been comparatively under-explored. Most existing Arabic approaches depend heavily on repetitive pre-processing, feature engineering, and external resources such as sentiment lexicons. To overcome these limitations, transfer learning using Arabic variants of the BERT language model provides an alternative methodology. Evaluating different BERT implementations on the standard HAAD reference dataset shows that these transfer learning models outperform traditional baselines as well as previously proposed approaches for Arabic aspect-based sentiment analysis.
Accurately capturing sentiments towards specific topics or features is vital for understanding public opinion and customer sentiment in Arabic. Moving away from manual feature engineering and static lexicons towards adaptable language models simplifies text processing pipelines and improves the accuracy of fine-grained sentiment analysis in Arabic digital text.
The models could enable improved customer review analytics, brand monitoring, and opinion mining tools for software vendors serving Arabic-speaking markets. At present, the research sits at an applied, laboratory-tested stage, having demonstrated success on a standard benchmark dataset. Progression towards commercial software would require testing on diverse, noisy commercial datasets and embedding the models into scalable data pipelines.
AI-generated from the published abstract. Always read the original work before citing.
Aspect-based sentiment analysis (ABSA) is a method used to identify the aspects discussed in a given text and determine the sentiment expressed towards each aspect. This can help provide a more fine-grained understanding of the opinions expressed in the text. The majority of Arabic ABSA techniques in use today significantly rely on repeated pre-processing and feature-engineering operations, as well as the use of outside resources (e.g., lexicons). In essence, there is a significant research gap in NLP with regard to the use of transfer learning (TL) techniques and language models for aspect term extraction (ATE) and aspect polarity detection (APD) in Arabic text. While TL has proven to be an effective approach for a variety of NLP tasks in other languages, its use in the context of Arabic has been relatively under-explored. This paper aims to address this gap by presenting a TL-based approach for ATE and APD in Arabic, leveraging the knowledge and capabilities of previously trained language models. The Arabic base (Arabic version) of the BERT model serves as the foundation for the suggested models. Different BERT implementations are also contrasted. A reference ABSA dataset was used for the experiments (HAAD dataset). The experimental results demonstrate that our models surpass the baseline model and previously proposed approaches.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3390/electronics12030515
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
