Arabic aspect sentiment polarity classification using BERT

TL;DR

This paper demonstrates that using BERT-based contextual embeddings significantly improves Arabic aspect sentiment polarity classification accuracy across multiple datasets, surpassing previous state-of-the-art models.

Contribution

It introduces a simple BERT-based neural baseline for Arabic aspect sentiment analysis, leveraging contextual embeddings and sentence pair input to enhance performance.

Findings

Achieved 89.51% accuracy on Arabic hotel reviews

Achieved 73% accuracy on human-annotated book reviews

Achieved 85.73% accuracy on Arabic news dataset

Abstract

Aspect-based sentiment analysis(ABSA) is a textual analysis methodology that defines the polarity of opinions on certain aspects related to specific targets. The majority of research on ABSA is in English, with a small amount of work available in Arabic. Most previous Arabic research has relied on deep learning models that depend primarily on context-independent word embeddings (e.g.word2vec), where each word has a fixed representation independent of its context. This article explores the modeling capabilities of contextual embeddings from pre-trained language models, such as BERT, and making use of sentence pair input on Arabic aspect sentiment polarity classification task. In particular, we develop a simple but effective BERT-based neural baseline to handle this task. Our BERT architecture with a simple linear classification layer surpassed the state-of-the-art works, according to the experimental results on three different Arabic datasets. Achieving an accuracy of 89.51% on the Arabic hotel reviews dataset, 73% on the Human annotated book reviews dataset, and 85.73% on the Arabic news dataset.