Causal Modeling of Twitter Activity During COVID-19

TL;DR

This paper introduces a causal inference method to analyze how COVID-19 pandemic characteristics influence Twitter activity and public sentiment, helping distinguish between correlated events and actual causes of public attention.

Contribution

It presents a novel causal modeling approach for Twitter data during COVID-19, enabling the identification of variables that causally impact public attention and sentiment.

Findings

Successfully captures epidemiological domain knowledge

Identifies variables affecting public attention and sentiment

Distinguishes between correlation and causation in public attention

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.