JURNAL RISET INFORMATIKA Vol. 5, No. 1. December 2022 P-ISSN: 2656-1743 |E-ISSN: 2656-1735 DOI: https://doi.org/10.34288/jri. v5i1.452 Accredited rank 3 (SINTA 3), excerpts from the decision of the Minister of RISTEK-BRIN No. 200/M/KPT/2020 459 Sentiment Analysis of Twitter's Opinion on The Russia and Ukraine War Using Bert Muhammad Fahmi Julianto -1 , Yesni Malau -2*) , Wahyutama Fitri Hidayat -3 Teknik Informatika Kampus Kota Pontianak 1 , Sistem Informasi Kampus Kota Pontianak 3 Universitas Bina Sarana Informatika fahmi.fjl@bsi.ac.id, wahyutama.wfh@bsi.ac.id Teknik Elektro 2 Universitas Bina Sarana Informatika 2*) yesni.ymu@bsi.ac.id (*) Corresponding Author Abstrak Berita mengenai perang yang terjadi antara Rusia dan Ukraina tidak dapat dipungkiri mempengaruhi berbagai aspek kehidupan di dunia. Hal tersebut mempengaruhi tulisan setiap warga dunia pada berbagai platform media sosial salah satunya twitter. Analisis sentimen merupakan proses identifikasi serta membuat kategori sentimen yang dilakukan secara komputasi. Proses Analisis sentiment dimaksudkan juga untuk membuat komputer memahami arti dari kalimat yang dituliskan oleh manusia dengan pemrosesan menggunakan algoritma. penelitian ini digunakan metode deep learning Bahasa model BERT (Bidirectional Encoder Representation form Transform) sebagai proses analisa sentimen yang ada pada twet yang dituliskan mengenai perang Rusia dan Ukraina oleh pengguna media sosial twetter. Sentimen akan dibagi kedalam tiga bagian yaitu positif, netral, serta negatif. Hyperparameters pada penelitian ini menggunakan 10 epoch, dengan learning rate 2e-5, serta batch size 16. Pengujian yang digunakan dalam analisis sentimen adalah model BERTbase Multilingual-cased-model serta hasil akurasi sebesar 97%. Saran untuk penelitian selanjutnya diperlukannya dataset yang lebih seimbang antara sentimen Positif, netral dan negatif. Melakukan imbalancing dataset sebelum melakukan training sehingga diharapkannya hasil yang lebih baik. Kata kunci: Perang, Rusia-Ukraina, Analisis Sentimen, BERT Abstract News about the war between Russia and Ukraine can not be denied affecting various aspects of life worldwide. It affects the writings of every citizen of the world 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 three parts: 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. Keywords: War, Russia-Ukraine, Sentiment Analysis, BERT INTRODUCTION Conflicts inevitably occur in everyday life, big or small. Many things can cause conflict, but conflict often arises because of differences in interests and can also be caused by domination and the desire to dominate. The conflict between Russia and Ukraine occurred over Crimea, Eastern Ukraine. Crimea itself has been a struggle for centuries. It looks at its history. Crimea was formerly known as Tauris or as