Pandemic Pulse: Unraveling and Modeling Social Signals during the COVID-19 Pandemic

TL;DR

This paper explores diverse social data sources to analyze societal responses during COVID-19, revealing trends in news coverage and political biases, and introduces a multimodal dataset for future social impact studies.

Contribution

It introduces a multimodal social data collection related to COVID-19 and provides initial analysis of news trends and political biases during the pandemic.

Findings

COVID-19 news articles peaked after WHO declaration and then declined.

Moderate and scientific sources published less COVID-19 news over time.

Preliminary analysis suggests political bias influences news coverage during the pandemic.

Abstract

We present and begin to explore a collection of social data that represents part of the COVID-19 pandemic's effects on the United States. This data is collected from a range of sources and includes longitudinal trends of news topics, social distancing behaviors, community mobility changes, web searches, and more. This multimodal effort enables new opportunities for analyzing the impacts such a pandemic has on the pulse of society. Our preliminary results show that the number of COVID-19-related news articles published immediately after the World Health Organization declared the pandemic on March 11, and that since that time have steadily decreased---regardless of changes in the number of cases or public policies. Additionally, we found that politically moderate and scientifically-grounded sources have, relative to baselines measured before the beginning of the pandemic, published a lower proportion of COVID-19 news than more politically extreme sources. We suggest that further analysis of these multimodal signals could produce meaningful social insights and present an interactive dashboard to aid further exploration.