Sentiment Analysis of student on Online Lectured During Covid-19 Pandemic Using K-Means and Naïve Bayes Classifier

Abstract


 
 
 
 The Covid-19 pandemic that occurred at the end of 2019 caused life changes, one of which was the learning process in universities. in accordance with the instructions issued by the Minister of Education as an effort to prevent the spread of Covid-19 by conducting online learning. Learning that is carried out online with a long period of time there are many obstacles such as networks and learning processes that are not optimal. Thus, students have mixed opinions on online lectures. Twiter is one of the social media used by students in expressing opinions on online lectures. The sentiment that users write on Twitter has not been determined in a more positive or negative direction. Sentiment analysis is needed to determine the tendency of student opinions towards online lectures. In this study, a sentiment analysis of online lectures was carried out using the K-Means and Naïve Bayes Classifier methods. The K-Means method is used to perform labeling or clustering and the Naïve Bayes Classifier is used as the classification. Based on research conducted with testing the Naïve Bayes Classifier model with a 70% division of training data and 30% test data using matrix confussion resulted in an accuracy of 95.67%.