Social media has become an excellent way to discover people’s thoughts about various topics and situations. In recent years, many studies have focused on social media during crises, including natural disasters or wars caused by individuals. This study examines how people expressed their feelings on Twitter during the Russian aggression on Ukraine. This study met two goals: the collected data was unique, and it used Machine Learning (ML) to classify the tweets based on their effect on people’s feelings. The first goal was to find the most relevant hashtags about aggression to locate the data set. The second goal was to use several well-known ML models to organize the tweets into groups. The experimental results have shown that most of the performed ML classifiers have higher accuracy with a balanced dataset. However, the findings of the demonstrated experiments using data balancing strategies would not necessarily indicate that all classes would perform better. Therefore, it is essential to highlight the importance of comparing and contrasting the data balancing strategies employed in Sentiment Analysis (SA) and ML studies, including more classifiers and a more comprehensive range of use cases.
Key words: Sentiment Analysis, Machine Learning, Classification Algorithm, Imbalanced Data Classification, Russian-Aggression in Ukraine
|
