Naïve Bayes algorithm in Twitter sentiment analysis; public attitude towards Covid-19 vaccination.

This digitalization phenomenon causes the dissemination of information to be very fast and everything to be very easy to access. In addition, social media has become a new platform that acts as a medium of communication in this digital era. The COVID-19 pandemic is forcing the government to move quickly in procuring vaccines. Nevertheless, various responses have emerged in the community, including those who think that the procurement of this vaccine is a conspiracy and those who support and are willing to volunteer for vaccine trials. So, it is necessary to do a sentiment analysis of this phenomenon. The Naive Bayes method is a popular algorithm used to classify data in sentiment analysis. This method is also suitable when applied to high-dimensional data. Another advantage of the Naive Bayes method is simple, fast, and has high accuracy in classifying. Data were used in this research are Tweet's data with the hashtag #vaksin accessed from January 12^th, 2021, to February 3^rd, 2021. Based on the analysis results, it is known that the Naive Bayes model with the value of Laplace smoothing is 0 has the highest accuracy value of 62.84% in classifying tweets into positive, negative, or neutral polarity. In addition, the results of sentiment analysis on tweets data are a positive sentiment polarity trend at 51%, negative sentiment at 5%, and neutral sentiment at 44%. [ABSTRACT FROM AUTHOR]

Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)