News about the war between Russia and Ukraine can not be denied affecting various aspects of life worldwide. It affects the writings of every world citizen on various social media platforms, one of which is Twitter. Sentiment analysis is a process of identifying and making sentiment categories computationally. The sentiment analysis process is also intended to make computers understand the meaning of human sentences by processing algorithms. This research uses the deep learning method of the BERT (Bidirectional Encoder Representation Form Transform) model language to analyze the sentiments in the tweets written about the wars between Russia and Ukraine by Twitter social media users. The sentiment will be divided into positive, neutral, and hostile. The hyperparameters in this study used ten epochs, with a learning rate of 2e-5 and a batch size of 16. The test used in sentiment analysis was the BERTbase Multilingual-cased-model model, and the accuracy was 97%. Suggestions for further research are the need for a more balanced dataset between positive, neutral, and negative sentiments. They reward the dataset before training so that better results are expected.
Copyrights © 2022