COMPARISON OF THE ACCURACY OF THE LEXICON-BASED AND NAIVE BAYES CLASSIFIER METHODS TO PUBLIC OPINIONS ABOUT REMOVING MASKS ON SOCIAL MEDIA TWITTER

ABSTRACT

At the beginning of 2020 the world was shocked by the COVID-19 pandemic which paralyzed all aspects of activity for some time. However, over time and with the discovery of a vaccine, the cases caused by COVID-19 began to subside. In 2022, the Indonesian government make a policy that people are allowed to take off their masks when active but are encouraged to maintain health protocols. However, the approach reaped the pros and cons of the Indonesian people. One challenge is to build technology to detect and summarize an overall those pros and cons. So that, we look at Twitter and build models for classifying ‘tweets' into positive, negative and neutral sentiment using top two approaches for sentiment analysis, the lexicon-based method and the naive Bayes classifier. This study aimed to analyze public opinion about removing masks through Twitter by comparing the lexicon-based method and the naive Bayes classifier method to find out how the community responded to taking off masks. A total of 639 tweets with the keyword "Lepas Masker" was analyzed include data crawling, text preprocessing, feature extractions and the classification process. The comparison of the results obtained shows the accuracy of 82% for the lexicon-based method and 70% for the naive Bayes classifier method. To the results, the accuracy value of the lexicon-based method is higher than the naive Bayes classifier method. © 2023 Little Lion Scientific. All rights reserved.