Sentiment Analysis From Twitter About Covid-19 Vaccination in Indonesia Using Naive Bayes and Xgboost Classifier Algorithm

Alvin Irwanto, Leonard Goeirmanto


The pandemic that hit the world has greatly impacted our life. But after some time, it seems that it will be going to end because the vaccine has already been made. In response to this, some people expressed their opinions about this vaccination on social media, for example, in the form of tweets on Twitter. The authors use those opinions or tweets as sentiment analysis material to determine the assessment of this vaccination. The tweet data in this study was obtained through data crawling using the Twitter API with the Python programming language. The variables used in this case are public tweets and their sentiments. This sentiment analysis process uses the Classification method with the Naive Bayes Classifier and will be compared with the XGBoost Classifier algorithm. The results of this study indicate that people are more likely to respond positively to this vaccination. In this case, the Naive Bayes Classifier got better performance with 0.95 from ROC - AUC Score and 134 ms in runtime compared to the XGBoost Classifier algorithm with 0.882 in ROC - AUC Score and 1 minute and 59 seconds in runtime.


Covid-19 vaccination; Naïve Bayes Classifier; Sentiment Analysis Twitter; XGboost Classifier;

Full Text:




  • There are currently no refbacks.

Published by:
Fakultas Teknik Universitas Mercu Buana
Jl. Raya Meruya Selatan, Kembangan, Jakarta 11650
Tlp./Fax: +62215871335
p-ISSN: 1410-2331
e-ISSN: 2460-1217
Journal URL:
Journal DOI: 10.22441/sinergi

Creative Commons License

Journal by SINERGI is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License

Analytics Made Easy - StatCounter
View My Stats

The Journal is Indexed and Journal List Title by: