Global News Synchrony During the Start of the COVID-19 Pandemic

Xi Chen, Scott A. Hale, David Jurgens, Mattia Samory, Ethan Zuckerman, Przemyslaw A. Grabowicz

Keywords: international news network, news event synchrony, computational social science

Abstract:

News coverage profoundly affects how countries and individuals behave in international relations. Yet, we have little empirical evidence of how news coverage varies across countries, languages, locations, political blocs, and time, because of challenges related to measuring and comparing news coverage at a global scale.

To address these challenges, we develop an efficient computational pipeline that comprises three components: 1) a transformer model to estimate multilingual news similarity; 2) a global event identification system that clusters news based on their similarity network; and 3) a method estimating and explaining the synchrony of news across countries and diversity of news within a country, measured based on the news coverage of global events. Each component achieves state-of-the art performance, scaling seamlessly to massive datasets of millions of news articles.

We apply the pipeline to study news articles published between January 1 and June 30, 2020, across 124 countries and 10 languages, and identify the factors explaining biases in national and international news coverage. Our analysis reveals that:

(1) news media tend to cover a more diverse set of events in countries that are internally varied: those with federalist governments, larger populations, more official languages, and higher inequality;
(2) news coverage is more synchronized between countries that not only actively participate in commercial and political relations---such as, pairs of countries with high bilateral trade volume, and countries that belong to the NATO military alliance or BRICS group of major emerging economies---but also countries that share certain traits---an official language, high GDP, and high democracy indices.

Track: Social Networks, Social Media, and Society

Submission Guidelines Scope: Yes

Submission Guidelines Blind: Yes

Submission Guidelines Format: Yes

Submission Guidelines Limit: Yes

Submission Guidelines Authorship: Yes

Student Author: Yes

Submission Number: 1954