Sentiment Analysis of Twitter's Opinion on The Russia and Ukraine War Using Bert

Abstract

News about the war that took place between Russia and Ukraine can not be denied affecting various aspects of life in the world. This 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 which is done computationally. Sentiment analysis process is also intended to make computers understand the meaning of sentences written by humans by processing using algorithms. This study uses a deep learning method using a language model, namely BERT (Bidirectional Encoder Representation Form Transformers) as a process of analyzing the sentiments that exist in tweets written about the war in Russia and Ukraine by twetter social media users. These sentiments will be divided into three parts, namely positive, neutral and negative. In this study, the hyperparameters used were 10 epochs, learning rate 2e-5, and batch size 16. The sentiment analysis test used the BERTbase Multilingual-cased-model model and the accuracy value obtained was 97%.

Keywords

• war
• russia-ukraine
• sentiment
• sentiment analysis
• bert