Comparison of Support Vector Machine and Random Forest Algorithms in Sentiment Analysis on Covid-19 Vaccination on Twitter Using Vader and Textblob Labelling
Berliana Putri Meliani, Oktariani Nurul Pratiwi, Rachmadita Andreswari · Advances in Social Science, Education and Humanities Research/Advances in social science, education and humanities research · 2022
Corona Virus Disease 2019 is a world outbreak that was first reported in Wuhan in December 2019.The first case of Covid-19 in Indonesia was confirmed on March 2, 2020.Covid-19 is caused by infection with virus named SARS-Cov-2.Currently, social media is widely used to find out public opinion.Generally, on Twitter social media, issues that are currently hot and much discussed by the public will become Trending Conversations.To find out and filter the opinions on social media, whether they include positive or negative opinions, you can use Sentiment Analysis.In this study, the sentiment analysis about covid-19 vaccination will use the Support Vector Machine (SVM) and Random Forest algorithms.The dataset will be labeled using the VaderSentiment and Textblob libraries found in Python.This comparison results that the SVM algorithm with textblob labeling produces an accuracy of 0.8940.Meanwhile, the sentiment results show that people tend to have negative opinions.Therefore, the best modeling for sentiment analysis is to use the Support Vector Machine with Textblob labeling.