Analisis Sentimen Mahasiswa di Surabaya Terhadap Pelayanan Vaksinasi COVID-19 Menggunakan Beberapa Classifier

Abstract

Indonesia is one of the countries that are currently struggling to deal with the COVID-19 virus pandemic by providing vaccination. The government is currently trying to persuade the public to do vaccination by maximizing COVID-19 vaccination services. In reality, vaccination services still have problems with some aspects. To see various insights on vaccination services that have been implemented, therefore a research was conducted in the field of sentiment analysis to analyze public opinion. In this research, classifiers that will be used are Naïve Bayes, Support Vector Machine (SVM), Random Forest, and Light Gradient Boosting Machine (LGBM) to perform text classification and their performances will be compared with evaluation metrics. There are two types of datasets used, namely questionnaire dataset and social media dataset. The questionnaire model will be tested using a social media dataset, while the social media model will use social media dataset that will be split. The testing results show that the model trained with the social media dataset produces better performance than the questionnaire model. Of these four classifiers, the best model for aspect and sentiment classification is Random Forest