<![CDATA[Classification is a process of identifying new data provided based on validation of previous data. One classification process that can be used is fake news classification. The classification process requires as little time as possible to get maximum results, so a faster method is needed to classify news. The BART algorithm can be a method that can be used to carry out classification and use Adam optimization to improve the performance of the algorithm. The aim of this research is to classify fake news, whether the BART algorithm and Adam optimization are able to provide good results and to label whether the news is fake or not. The results of this process are based on the use of a dataset of 65% for training, 30% for validation, and 5% to produce 2 BART models. With the additional use of Adam optimization and several other parameters for the training process, the first model was able to provide accuracy performance of 92.88%, training loss reached 12.2%, and validation loss reached 28.4% and the second model produced an accuracy of 92.63 %, training loss 15% and validation loss reaching 20.2%. In the first model, it can predict 105 data labeled negative and 1306 positive data. Meanwhile, the second model was able to predict 128 data labeled negative and 1283 positive data.]]>
Copyrights © 2024
