<![CDATA[YouTube is a social media site that is quite familiar and is used as a means of disseminating video-based information. With a fairly high number of users, YouTube can become a communication medium for audiences, including government agencies. The user’s responses in comments reflect the nuance of the presented video. This research aims to determine the best algorithm for classifying video types based on user comments. Several machine learning algorithms used to carry out classification are Decision Tree, Random Forest, K-Nearest Neighbor, Support Vector Machine, and Logistic Regression. K-Fold Cross Validation was chosen as a method to evaluate the performance of classification algorithms based on the accuracy values. of these algorithms in classifying YouTube videos based on comments. The first experiment with the highest ratio of training and test data for each algorithm was obtained at a ratio of 90:10, with respectively 78.99%, 86.21%, 84.01%, 72.72%, and 79.31%. In the second experiment with k-fold cross validation using a ratio of 90:10, the highest accuracy for each algorithm was obtained at a value of k = 10, which was respectively 74.39%, 81.34%, 78.05%, 85.21%, and 72.15%. From these results, it can be concluded that the most suitable algorithm for classifying YouTube videos based on comments is the Random Forest algorithm with a training and test data ratio of 90:10 and SVM with 10-cross-fold validation. These results show that a larger portion of data for learning has a positive impact on algorithm performance.]]>
Copyrights © 2024
