Sentiment Analysis towards Face-to-Face School Activities During the COVID-19 pandemic in Indonesia

As the COVID-19 pandemic took place, many face-to-face activities have been stopped to suppress the spread. However, in the last few months, many of those activities including learning activities have started to switch from online back to face-to-face. One of the major activities is face-to-face learning activities which involve millions of students all over Indonesia. Consequently, this study focuses on analyzing public sentiment through Twitter tweets which were obtained through scrapping by using Tweepy. The tweets were labeled using a semi-automatic process, using TextBlob and manual annotation. Next, we trained an IndoBERT model to conduct sentiment analysis and found that public sentiment was dominated by a mix of both negative and positive sentiment, followed by neutral sentiment. Our model obtained an accuracy of 40.79% on unseen data.