Towards Predicting COVID-19 Trends: Feature Engineering on Social Media Responses   [open pdf - 773KB]

From the Document: "On January 14, 2020, the World Health Organization (WHO) reported the novel coronavirus (COVID-19) to be potentially transmitted by human contact. [...] The United States of America (U.S.A) was hit with its first COVID-19 cases on January 21, 2020, which was later confirmed on February 26, 2020 (Jorden et al., 2020). During this time, the Centers for Disease Control and Prevention (CDC) began to spread information about the COVID-19 virus through social media channels. [...] Quickly following this the U.S.A halted as the cases in New York began to rapidly increase starting in late February (Thompson et al., 2020). In return cities around the U.S.A seeing what happened in New York began to enforce social distancing mandates, the wearing of mask and the closure of non-essential businesses and activities such as churches, bars, beaches, etc. Although this pandemic became a common thread around the world, it wasn't the only commonality. The world had lockdowns, social distancing protocols, and mask mandates in common. With social distancing protocols in place, we noticed the use of social networking increase dramatically as users attempted to keep in contact. This made individuals within all generations increase their use of social media. Social media platforms such as Twitter had a 24% increase in daily users in relation to its previous year. Users new and old flocked to Twitter as they began to vocalize their concerns about the government's plan."

Information Systems for Crisis Response and Management (ISCRAM), Posted here with permission. Documents are for personal use only and not for commercial profit.
Retrieved From:
Information Systems for Crisis Response and Management (ISCRAM): http://idl.iscram.org/
Media Type:
Proceedings of the 18th ISCRAM Conference. Blacksburg, VA. May 2021
Help with citations