Sentiment Analysis of Google Classroom Application Using Machine Learning Techniques

This research analyzes the social sentiment of the academic community towards the digital education platform Google Classroom. Artificial intelligence algorithms such as Naïve Bayes, K-Nearest Neighbor (KNN), and Random Forest are implemented to perform sentiment analysis based on Play Store comment data. The dataset is 7000 comments from the academic community on the Google Classroom application, and the best model of the three algorithms is selected based on the accuracy, precision, recall, and f1 values. The results showed that the Random Forest algorithm produced the highest accuracy of 84.05%. Naïve Bayes algorithm with a multinomial model produces the highest accuracy of 83.96%. Meanwhile, KNN produces an accuracy of 77.96%. This research illustrates how artificial intelligence algorithms can be applied to analyze sentiment in observing the social behavior of the communities towards digital education applications. This can be the basis for effective improvement of the app user experience.