Monitoring the Dynamics of Emotions during COVID-19 Using Twitter Data

The novel COVID-19 is one of the most serious health pandemics in our time. According to the World Health Organization (WHO), it has been spread over more than 150 countries and territories worldwide with thousands of deaths. In this research, we propose a framework to explore the dynamics and flow of behavioral changes among twitter users during the pandemic. In our framework, the related tweets are retrieved from the Twitter social network in three different time intervals and stored in our data repository. After cleaning and pre-processing the data, using natural language processing and social network analysis techniques, a set of emotions is extracted from them along with their sentiment characteristics. Further, the data is visualized in order to identify the changing patterns. The results of this project show significant connections between the infection and mortality rates and the emotional characteristics of the twitter users.