Sentiment Analysis of Public Opinions Regarding "Ideas of Presidential Candidates" in YouTube Video Comments with Robustly Optimized BERT Pretraining Approach

Sumihar, Yoel Pieter

Jusikom: Jurnal Sistem Informasi Ilmu Komputer
Vol. 8 No. 1 (2024): JUSIKOM: JURNAL SISTEM INFROMASI ILMU KOMPUTER

Social media and video-sharing platforms such as YouTube have become one of the primary sources of information and social interaction in modern society. In politics, YouTube has become essential for spreading ideas, campaign platforms, and opinions about the presidential election. Using the pre-trained Indonesian Roberta Base Sentiment Classifier Model, the data obtained from YouTube comments will be divided into three labels: positive, negative, and neutral. The results of this study are the accuracy for each sentiment label, where the value for positive is 93%, the negative is 90.5%, and the neutral is 93.04%. Residents give more positive comments to presidential candidate Prabowo Subianto, with a positive value of 54.13%, followed by Anies Baswedan at 42.8% and Ganjar Pranowo at 31.91%.