PABSA: Hybrid Framework for Persian Aspect-Based Sentiment Analysis

TL;DR

This paper tackles Persian aspect-based sentiment analysis under low-resource constraints. It proposes a hybrid ML-DL framework that blends multilingual-BERT polarity signals as auxiliary features into a decision-tree classifier and augments data with a Persian synonym and named-entity dictionary. The approach achieves 93.34% accuracy (92.0% F1) on Pars-ABSA, surpassing state-of-the-art Persian ABSA models. The study also provides new linguistic resources for Persian NLP and demonstrates the value of combining contextual embeddings with structured classifiers for robust sentiment analysis in low-resource languages. The results have practical implications for Persian social media monitoring, e-commerce sentiment analytics, and broader low-resource NLP tasks.

Abstract

Sentiment analysis is a key task in Natural Language Processing (NLP), enabling the extraction of meaningful insights from user opinions across various domains. However, performing sentiment analysis in Persian remains challenging due to the scarcity of labeled datasets, limited preprocessing tools, and the lack of high-quality embeddings and feature extraction methods. To address these limitations, we propose a hybrid approach that integrates machine learning (ML) and deep learning (DL) techniques for Persian aspect-based sentiment analysis (ABSA). In particular, we utilize polarity scores from multilingual BERT as additional features and incorporate them into a decision tree classifier, achieving an accuracy of 93.34%-surpassing existing benchmarks on the Pars-ABSA dataset. Additionally, we introduce a Persian synonym and entity dictionary, a novel linguistic resource that supports text augmentation through synonym and named entity replacement. Our results demonstrate the effectiveness of hybrid modeling and feature augmentation in advancing sentiment analysis for low-resource languages such as Persian.