Understanding COVID-19 News Coverage using Medical NLP

TL;DR

This paper analyzes COVID-19 news coverage from CNN and The Guardian using advanced medical NLP models to uncover biases, key medical concepts, and the impact on public perception and vaccine hesitancy.

Contribution

It introduces a comprehensive analysis of COVID-19 news articles using clinical NLP models to identify medical concepts, biases, and influence on vaccine attitudes.

Findings

Identification of key medical entities and phrases in news articles

Detection of biases and changes in coverage over time

Insights into how adverse drug event reporting affects vaccine hesitancy

Abstract

Being a global pandemic, the COVID-19 outbreak received global media attention. In this study, we analyze news publications from CNN and The Guardian - two of the world's most influential media organizations. The dataset includes more than 36,000 articles, analyzed using the clinical and biomedical Natural Language Processing (NLP) models from the Spark NLP for Healthcare library, which enables a deeper analysis of medical concepts than previously achieved. The analysis covers key entities and phrases, observed biases, and change over time in news coverage by correlating mined medical symptoms, procedures, drugs, and guidance with commonly mentioned demographic and occupational groups. Another analysis is of extracted Adverse Drug Events about drug and vaccine manufacturers, which when reported by major news outlets has an impact on vaccine hesitancy.