SoBigDemicSys: A Social Media based Monitoring System for Emerging Pandemics with Big Data

The outbreak of Covid-19 pandemic has caused millions of people infected and dead, resulting in global economy depression. Lessons learned to minimize the damage in an emerging pandemic is that timely tracking and reasonable trend prediction are required to help the society (e.g., municipality, institutions, and industries) with timely planning for efficient resource preparation and allocation. This paper presents a system to monitor the pandemic trends, analyze the correlation and impacts, predict the evolution, and visualize the prediction results to end users as social indicators. The significance lies in the fact that tracing online information collection for pandemic related prediction has less time lag, cheaper cost, and more potential information indicators. Demo video is available at https://vimeo.com/711930134.

I. Introduction

The pandemic evolution has been previously tracked and projected using the statistic report (e.g., confirmed and death cases). Despite the significant technological leaps in pandemic surveillance, the very recent COVID-19 evidently showed the vulnerabilities of our modern society in response to the emerging pandemic. To complement the traditional indicator-based surveillance through government reports, online resources through AI techniques showed its advantages in early detection and further forecasting of emerging pandemics. For example, the peak of search volume on COVID-19 pandemic was 20 days earlier than the issuance of official warnings [1]. Online platforms provide rich information to anticipate and explain the course of outbreaks while also reflecting public knowledge and perceptions when used in a timely manner to assist official surveillance. Fig.1 illustrates our motivation examples, which show different stances of web users on the COVID-19 pandemic and the government regulations.