Analisa Sentimen Efektifitas Vaksin terhadap Varian COVID 19 Omicron Berbasis Leksikon

Abstract

One of the ways to control the spread of COVID-19 is vaccination. However, discussions about the effectiveness of vaccines are still visible, especially in various social media. Not yet finished about this, now a new variant of covid 19 has emerged, namely Omicron. The news through the youtube channel is also sought after and seen by people to find out what this omicron virus looks like and the effectiveness of the vaccine that has been carried out by the community against this new virus. In this study, the detection of public opinion about the effectiveness of vaccination using the Support Vector Machine algorithm. The dataset was taken by crawling the YouTube comments of English news channels and then labeling lexicon-based comments using TextBlob and VADER into positive, negative, and neutral comments. There are differences in the number of positive, negative, and neutral comments with the two text labeling methods, but not too far. The application of the SVM algorithm to the dataset with the comment labeling of the TextBlob method resulted in an accuracy of 63%, while the application of the SVM with the comment labeling of the VADER method resulted in an accuracy of 70%.