RUemo—The Classification Framework for Russia-Ukraine War-Related Societal Emotions on Twitter through Machine Learning

The beginning of this decade brought utter international chaos with the COVID-19 pandemic and Russia-Ukraine war (RUW). ongoing has been building pressure across globe. People have showcasing their opinions through different communication media, which social media is prime source. Consequently, it important to analyze people’s emotions toward RUW. This paper therefore aims provide framework for automatically classifying distinct societal on Twitter, utilizing amalgamation Emotion Robustly Optimized Bidirectional Encoder Representations from Transformers Pre-training Approach (Emoroberta) machine-learning (ML) techniques. combination shows originality our proposed framework, i.e., War (RUemo), in context We utilized Twitter dataset related RUW available Kaggle.com. RUemo can extract 27 users that are further classified by ML achieved 95% testing accuracy multilayer perceptron logistic regression techniques multiclass emotion classification task. Our key finding indicates that:First, 81% survey show a neutral position RUW; second, there evidence bots posting RUW-related tweets; third, other than Russia Ukraine, mentioned countries such as Slovakia USA; fourth, accounts Ukraine President US also users. Overall, majority tweets describe terms more Russia.