Coffee is known as an international commodity. Two types of coffee beans have a high commercial value, namely Arabica and Robusta. Indonesia is the largest producer of Robusta coffee in the world, and Lampung Province is the best producer of Robusta coffee in Indonesia. People have a lot of opinions about the Robusta coffee from Lampung because of its specialty. This research aims to analyze the sentiment towards Lampung Robusta Coffee based on comments on YouTube. This research aims to analyze the sentiment of Lampung Robusta Coffee on YouTube. This research uses AI methods such as Support Vector Machine (SVM), Naïve Bayes, and K-Nearest Neighbor (KNN) algorithms. We also considered balanced and unbalanced datasets and adopted a data-balancing approach. Overall, the sentiment towards Robusta coffee is mostly positive, with 145 instances (71.4%) expressing positive sentiment and 48 instances (28.6%) expressing negative sentiment. Among the three classification methods, support vector machines achieved the highest accuracy of 82.82% when matching the data with SMOTE, followed by Naive Bayes with 79.54% and K-Nearest Neighbors with 77.38%. The results of this study conclude that the SVM algorithm has the best accuracy on the YouTube comment dataset used in this study.