Open AccessSentiment Analysis Covid-19 Vaccination on Twitter Social Media Using Naïve Bayes Method
Author(s) -
Dihin Muriyatmoko,
Triana Harmini,
Maulana Kemal Ardiansyah
Publication year - 2021
Publication title -
procedia of engineering and life science
Language(s) - English
Resource type - Journals
ISSN - 2807-2243
DOI - 10.21070/pels.v2i0.1144
Subject(s) - logistic regression , social media , covid-19 , public opinion , vaccination , government (linguistics) , naive bayes classifier , sentiment analysis , bayes' theorem , computer science , support vector machine , artificial intelligence , medicine , political science , world wide web , machine learning , virology , bayesian probability , politics , linguistics , philosophy , disease , pathology , infectious disease (medical specialty) , law
The government regulations regarding the implementation of vaccinations to tackle the COVID-19 pandemic. The regulation was issued by the Minister of Health Number ten of 2021. This program raises pros and cons so that it requires feedback for evaluation. Feedback can be obtained from opinions and stories that users convey through social media such as Twitter. This study aims to develop a model to determine public sentiment towards Covid-19 vaccination in three topics, namely the vaccination program, the effect of vaccination and the Covid-19 vaccine. The classification method used in this research is Bernoulli Naïve Bayes and Logistic Regression. The results of the comparison of the two methods show that Bernoulli Naïve Bayes gets better accuracy results. The number of tweet messages processed from Twitter is 5877. The model was tested to read public sentiment on Twitter from 7 September to 21 September 2021. The model concluded that public opinion regarding the vaccination program and the effect of vaccination tended to be positive. And opinions regarding the Covid-19 vaccine topic tend to be neutral. For further research, it can be developed by adding datasets.