Enhancing Aspect-based Sentiment Analysis with ParsBERT in Persian Language

TL;DR

This paper improves Persian aspect-based sentiment analysis by leveraging ParsBERT and a lexicon, achieving higher accuracy and efficiency in analyzing user opinions from Persian e-commerce data.

Contribution

It introduces a novel aspect-based sentiment analysis approach using ParsBERT combined with a lexicon, tailored for Persian language processing.

Findings

Achieved 88.2% accuracy in sentiment classification.

F1 score of 61.7 demonstrating balanced precision and recall.

Enhanced semantic understanding of Persian user opinions.

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.