<![CDATA[Bring Me The Horizon's song "Lost" received a wide response on YouTube, evident in the thousands of comments containing a variety of responses ranging from support and criticism to neutral opinions. The rapid development of social media has made it easier for people to freely share their views and experiences on musical works without being bound by space and time. YouTube, as one of the largest video-sharing platforms, plays a crucial role in documenting public perception of the song. This study was conducted to analyze listener sentiment towards the song "Lost" based on YouTube comments using the Support Vector Machine (SVM) algorithm and the Term Frequency–Inverse Document Frequency (TF-IDF) feature extraction technique. Comments were collected through web scraping from the song's official video, then processed through case folding, punctuation removal, tokenizing, stopword removal, and stemming to produce clean and uniform data. Term weights were calculated using TF-IDF and then used to label positive, negative, and neutral sentiments. The SVM model was built from training data and tested with test data to evaluate its performance using accuracy, precision, recall, and f1-score metrics so that classification quality could be assessed comprehensively. Based on the test results, the SVM algorithm was able to classify listener comments with 94% accuracy, with a distribution of negative sentiment of 207 comments, neutral comments of 1,280, and positive comments of 732. These findings demonstrate the effectiveness of SVM in analyzing the sentiment of song comments on social media and provide a more comprehensive picture of the public's view of Bring Me the Horizon's song "Lost.".]]>
Copyrights © 2026
