Utilizing distilBert transformer model for sentiment classification of COVID-19's Persian open-text responses

TL;DR

This paper presents a DistilBERT-based NLP model for sentiment analysis of Persian open-text responses related to COVID-19, achieving over 82% accuracy in detecting positive and negative sentiments.

Contribution

The study introduces a transformer-based sentiment classification approach specifically tailored for Persian COVID-19 survey responses, with comparative analysis of three methods.

Findings

Best model accuracy: 82.4%

Precision: 82.4%

Recall: 79.8%

Abstract

The COVID-19 pandemic has caused drastic alternations in human life in all aspects. The government's laws in this regard affected the lifestyle of all people. Due to this fact studying the sentiment of individuals is essential to be aware of the future impacts of the coming pandemics. To contribute to this aim, we proposed an NLP (Natural Language Processing) model to analyze open-text answers in a survey in Persian and detect positive and negative feelings of the people in Iran. In this study, a distilBert transformer model was applied to take on this task. We deployed three approaches to perform the comparison, and our best model could gain accuracy: 0.824, Precision: 0.824, Recall: 0.798, and F1 score: 0.804.