ANALISIS SENTIMEN GAYA HIDUP SLOW LIFE PADA MEDIA SOSIAL TWITTER

The digital age has given rise to Hustle Culture, which emphasizes high productivity but risks causing burnout. As an alternative, the slow life movement offers a more balanced lifestyle. Previous sentiment analysis on Twitter has been limited in multi-class classification and model comparison. This study addresses this gap by classifying sentiments related to slow life using four feature extraction methods (TF-IDF, BoW, N-grams). Evaluation was conducted by comparing six machine learning algorithms, deep learning models, and transformers (IndoBERTweet).