Global News Synchrony and Diversity During the Start of the COVID-19 Pandemic (2405.00280v1)

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. To enable studies of global news coverage, we develop an efficient computational methodology that comprises three components: (i) a transformer model to estimate multilingual news similarity; (ii) a global event identification system that clusters news based on a similarity network of news articles; and (iii) measures of news synchrony across countries and news diversity within a country, based on country-specific distributions of news coverage of the global events. Each component achieves state-of-the art performance, scaling seamlessly to massive datasets of millions of news articles. We apply the methodology to 60 million news articles published globally between January 1 and June 30, 2020, across 124 countries and 10 languages, detecting 4357 news events. We identify the factors explaining diversity and synchrony of news coverage across countries. Our study reveals that news media tend to cover a more diverse set of events in countries with larger Internet penetration, more official languages, larger religious diversity, higher economic inequality, and larger populations. Coverage of news events 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.

• The paper introduces a novel computational framework that analyzes global news synchrony and domestic diversity during the COVID-19 onset.
• It employs a transformer-based bi-encoder model and a clustering approach to identify 4,357 distinct news events from 60 million articles in 10 languages.
• Findings reveal that internet penetration boosts news diversity, while bilateral trade significantly drives international news alignment.

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

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

Introduction

This paper investigates global media dynamics during an unprecedented global event, the onset of the COVID-19 pandemic. The paper develops a computational framework to analyze multilingual news coverage, uncovering patterns of news synchrony between countries and the diversity of news within a country. By examining 60 million news articles published in the first half of 2020 across 124 countries and 10 languages, the authors identify systematic factors influencing international news synchrony and national news diversity.

Methodological Contributions

The methodology proposed by the authors is extensive and includes several innovative components:

1. Transformer Model for Multilingual News Similarity: The authors introduce a transformer-based bi-encoder model trained on a nuanced dataset of annotated news article pairs. This model efficiently computes pairwise similarity scores between news articles across different languages.
2. Global Event Identification System: A new clustering approach based on a global similarity network is employed to detect 4,357 distinct news events from the corpus.
3. Measures of News Synchrony and Diversity: By quantifying the coverage of these events, the authors compute synchrony between countries' news and diversity within a country, yielding metrics based on Shannon's entropy and Jensen-Shannon divergence.

Results and Discussion

The extensive dataset and robust methodology yield several noteworthy findings. Quantitatively, Internet penetration emerges as the strongest predictor of news diversity within countries, contrary to previous assertions that online news homogenizes media content. Conversely, factors such as population size, linguistic diversity, and economic inequality are also significant contributing factors.

For international news synchrony, the volume of bilateral trade stands out as the most significant factor, reinforcing the connection between economic ties and media coverage alignment. Countries belonging to political and economic blocs (e.g., NATO, BRICS) show higher news synchrony, which likely results from shared geopolitical interests and collective activities. Interestingly, while geographic proximity (contiguity and continental belonging) facilitates synchrony, the physical distance, given modern communication technologies, has become a less significant deterrent.

Implications

The findings offer deep insights into the interplay between national and international factors in shaping media coverage during major global events. Practically, the research could aid media organizations and policymakers in understanding coverage biases and audience influence across different regions. Theoretically, it challenges traditional notions of media homogenization in the digital era, opening avenues for future research in computational social science and global media studies.

Future Directions

The capabilities demonstrated in this research could be extended to longitudinal studies encompassing multiple years, analyzing trends in global news coverage over time. Such investigations could examine how coverage dynamics evolve in response to different types of global events, such as economic crises, political upheavals, or natural disasters. Additionally, the detection and analysis of biases, particularly in regions with conflicting relations, could inform the strategies of media monitoring and fair reporting practices.

In conclusion, this paper's comprehensive approach and empirical findings significantly advance the understanding of global news coverage and set a solid foundation for future studies in agenda-setting and international news flow. The authors' contributions, both methodological and empirical, are pertinent for comprehensively mapping how global and local factors jointly shape the media landscape during significant global phenomena.