Enhancing Aspect-based Sentiment Analysis with ParsBERT in Persian Language

2025-02-03

AI Summary

To address data scarcity and insufficient fine-grained sentiment recognition in Persian sentiment analysis, this paper proposes a ParsBERT-based aspect-level sentiment analysis method, integrating, for the first time, a domain-adapted Persian sentiment lexicon. Methodologically, we employ the ParsBERT pre-trained language model, design an aspect-aware classification head, and enhance token embeddings via lexicon-guided semantic augmentation, followed by joint fine-tuning. Experiments on the Digikala user review dataset achieve 88.2% accuracy and 61.7% F1-score, significantly outperforming baseline models. Our key contributions are: (1) the first adaptation of ParsBERT to Persian aspect-level sentiment analysis; (2) a lexicon-guided semantic enhancement mechanism that improves modeling of implicit sentiment polarities; and (3) a reusable technical framework for fine-grained sentiment analysis in low-resource languages.

Technology Category

• Natural Language Processing: Lexical Semantics and Morphology
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Evaluation and Analysis

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

In the era of pervasive internet use and the dominance of social networks, researchers face significant challenges in Persian text mining including the scarcity of adequate datasets in Persian and the inefficiency of existing language models. This paper specifically tackles these challenges, aiming to amplify the efficiency of language models tailored to the Persian language. Focusing on enhancing the effectiveness of sentiment analysis, our approach employs an aspect-based methodology utilizing the ParsBERT model, augmented with a relevant lexicon. The study centers on sentiment analysis of user opinions extracted from the Persian website 'Digikala.' The experimental results not only highlight the proposed method's superior semantic capabilities but also showcase its efficiency gains with an accuracy of 88.2% and an F1 score of 61.7. The importance of enhancing language models in this context lies in their pivotal role in extracting nuanced sentiments from user-generated content, ultimately advancing the field of sentiment analysis in Persian text mining by increasing efficiency and accuracy.

Problem

• Persian Language
• Sentiment Analysis
• Data Scarcity

Innovation

• ParsBERT
• Persian Sentiment Analysis
• Improved Accuracy