CVAS: An Interactive Visual Analytics System for Exploring COVID-19 Information on the Web
Tao Yang, Yixuan Zhou, Dan Feng, Haibo Hu · 2022
The outbreak of COVID-19 has been a critical social event in the past two years. The pandemic has seriously affected the world. Meanwhile, various forms of data about COVD-19 emerge on the Web endlessly, such as SNS discussions, Press releases, WHO statistics, etc. It is valuable work for government departments, news media, and health organizations to integrate and analyze these pandemics-related multi-source data on the web. In this work, we propose an interactive visual analytics system as CVAS that aims at mining and analyzing multi-source data concerned with COVD-19. Having been inspired by the Sankey diagram, we developed a view elaborately. Through appropriate interactions, massive patients’ mobility data can be visualized, thus showing the spread features of the pandemic in time and space more specifically. In addition, we collected more than 10,000 trending topics and nearly 10 million related comments on the SNS as Sina Weibo. We performed NLP to analyze their sentiment, identifying key events since the outbreak and the impact of the pandemic on public sentiment. Part of our work was awarded at the China visualization and visual analysis conference (ChinaVis2020) and recognized by peers.