Examining Emotional Reactions to the COVID-19 Crisis Through Twitter Data Analysis: A Comparative Study of Classification Techniques

Abstract

COVID-19 has significantly impacted peoples’ mental health because of isolation and social distancing measures. It practically impacts every segment of people’s daily lives and causes a medical problem that spreads throughout the entire world. This pandemic has caused an increased emotional distress. Since everyone has been affected by the epidemic physically, emotionally, and financially, it is crucial to examine and comprehend emotional reactions as the crisis affects mental health. This study uses Twitter data to understand what people feel during the pandemic. We collected Twitter data about COVID-19 and isolation, preprocessed the text, and then classified the tweets into various emotion classes. The data are collected using the twarc library and the Twitter academic researcher account and labeled using a Vader analyzer after preprocessing. We trained five machine learning models, namely, support vector machine (SVM), Naïve Bayes, KNN, decision tree, and logistic regression to find patterns and trends in emotions. The emotional reactions of individuals to the COVID-19 crisis are then analyzed. We applied precision, recall, F1-score, and accuracy as the evaluation metrics, which shows that SVM has performed best among other models. Our results show that isolated people felt various emotions, out of which, fear, sadness, and surprise were the most common. This study gives insights into the emotional impact of the pandemic and shows the power of Twitter data in understanding mental health outcomes. Our findings can be used to develop targeted interventions and support strategies to address the emotional toll of the pandemic.