Sentiment Analysis of Public Comments on YouTube Regarding the Inaugural Speech of the 8th President of Indonesia Using VADER and BERT Methods

The research examines public reactions toward President Prabowo Subianto first presidential address in 2024 by studying YouTube comment sentiments. By utilizing sentiment analysis methods, this research combines two main approaches: The research combines VADER (Valence Aware Dictionary and Sentiment Reasoner) for initial sentiment labeling through predefined dictionary categories with BERT (Bidirectional Encoder Representations from Transformers) for more advanced classification. The dataset contains 10,306 comments which display a range of public opinions. Positive sentiment represents 4,943 comments which make up 49.26% of the total while neutral sentiment accounts for 4,336 comments at 43.21% and negative sentiment represents 756 comments at 7.53%. The BERT model reached an accuracy level of 97.01% which illustrates its capability to process contextual details and subtle data elements. VADER delivers rapid preliminary labeling results and BERT improves classification precision through its analysis of complex contexts. The study reveals how people perceive the new government while providing chances for creating public opinion monitoring techniques for social and political topics. Researchers, academics, and policymakers will find these findings valuable for comprehending public opinion dynamics during the digital age's continuous evolution