Causal Modeling of Twitter Activity during COVID-19

Oguzhan Gencoglu,Mathias Gruber

doi:10.3390/computation8040085

Abstract

Understanding the characteristics of public attention and sentiment is an essential prerequisite for appropriate crisis management during adverse health events. This is even more crucial during a pandemic such as COVID-19, as primary responsibility of risk management is not centralized to a single institution, but distributed across society. While numerous studies utilize Twitter data in descriptive or predictive context during COVID-19 pandemic, causal modeling of public attention has not been investigated. In this study, we propose a causal inference approach to discover and quantify causal relationships between pandemic characteristics (e.g., number of infections and deaths) and Twitter activity as well as public sentiment. Our results show that the proposed method can successfully capture the epidemiological domain knowledge and identify variables that affect public attention and sentiment. We believe our work contributes to the field of infodemiology by distinguishing events that correlate with public attention from events that cause public attention.

Highlights

On 11 March 2020, Coronavirus disease 2019 (COVID-19) was declared a pandemic by the WorldHealth Organization [1] and more than 30 million people have been infected by it as of 19 September2020 [2]
A sharp increase in Twitter activity is observed after 28–29 February, which corresponds to the period of each country having at least one confirmed COVID-19 case
Different families of attributes are colored differently for ease of inspection—blue for COVID-19 pandemic related variables, yellow for country-specific statistics, green for government interventions, and red for representing variables related to public attention and sentiment in Twitter

Summary

Introduction

On 11 March 2020, Coronavirus disease 2019 (COVID-19) was declared a pandemic by the WorldHealth Organization [1] and more than 30 million people have been infected by it as of 19 September2020 [2]. Numerous studies proposed and utilized Twitter as a data source for extracting insights on public health as well as insights on public attention during the COVID-19 pandemic. Focus of these studies include content analysis [15], topic modeling [16], sentiment analysis [17], nowcasting or forecasting of the disease [18], early detection of the outbreak [19], quantifying and detecting misinformation, disinformation, or conspiracies [20], and measuring public attitude towards relevant health concepts (e.g., social distancing or working from home) [21]

Methods

Results

Discussion

Conclusion