Sentiment Analysis of COVID-19 Public Activity Restriction (PPKM) Impact using BERT Method

TL;DR

This study employs IndoBERT to analyze public sentiment on PPKM policies in Indonesia during COVID-19, demonstrating superior accuracy over classical methods like SVM and Naive Bayes.

Contribution

It introduces the use of IndoBERT for sentiment analysis of COVID-19 policy impact on social media data in Indonesia, showing improved performance over traditional models.

Findings

IndoBERT achieved an F1 score of 84%.

IndoBERT outperformed SVM and Naive Bayes.

Sentiment analysis can inform policy evaluation.

Abstract

Covid-19 has grown rapidly in all parts of the world and is considered an international disaster because of its wide-reaching impact. The impact of Covid-19 has spread to Indonesia, especially in the slowdown in economic growth. This was influenced by the implementation of Community Activity Restrictions (PPKM) which limited community economic activities. This study aims to analyze the mapping of public sentiment towards PPKM policies in Indonesia during the pandemic based on Twitter data. Knowing the mapping of public sentiment regarding PPKM is expected to help stakeholders in the policy evaluation process for each region. The method used is BERT with IndoBERT specific model. The results showed the evaluation value of IndoBERT f-1 score reached 84%, precision 86%, and recall 84%. Meanwhile for the evaluation of the use of SVM f-1 score 70%, 72% precision, and 70% recall. Multinominal Na\"ive Bayes evaluation shows f-1 score 83%, precision 78%, and recall 80%. As a conclusion, BERT method with the IndoBERT model is proven to be higher than classical methods such as SVM and Multinominal Na\"ive Bayes.