CoronaVis: A Real-time COVID-19 Tweets Data Analyzer and Data Repository (2004.13932v2)

Abstract: Due to the nature of the data and public interaction, twitter is becoming more and more useful to understand and model various events. The goal of CoronaVis is to use tweets as the information shared by the people to visualize topic modeling, study subjectivity, and to model the human emotions during the COVID-19 pandemic. The main objective is to explore the psychology and behavior of the societies at large which can assist in managing the economic and social crisis during the ongoing pandemic as well as the after-effects of it. The novel coronavirus (COVID-19) pandemic forced people to stay at home to reduce the spread of the virus by maintaining social distancing. However, social media is keeping people connected both locally and globally. People are sharing information (e.g. personal opinions, some facts, news, status, etc.) on social media platforms which can be helpful to understand the various public behavior such as emotions, sentiments, and mobility during the ongoing pandemic. In this work, we develop a live application to observe the tweets on COVID-19 generated from the USA. In this paper, we have generated various data analytics over a period of time to study the changes in topics, subjectivity, and human emotions. We also share a cleaned and processed dataset named CoronaVis Twitter dataset (focused on the United States) available to the research community at https://github.com/mykabir/COVID19. This will enable the community to find more useful insights and create different applications and models to fight with COVID-19 pandemic and future pandemics as well.