JMIR Publications

ABSTRACT

Background:

To investigate the impacts of the COVID-19 pandemic on the health and care workforce, we aimed to develop a framework that synergizes Natural Language Processing (NLP) techniques and human-generated analysis to reduce, organize, classify, and analyze a vast volume of publicly available news articles to complement scientific literature and support strategic policy dialogue, advocacy, and decision-making.

Objective:

The aim of this study was to explore the possibility of systematically scanning intelligence from media that are usually not captured or best gathered through structured academic channels and inform on the impacts of COVID-19 on the health workforce, contributing factors to the pervasiveness of the impacts, and policy responses, as depicted in publicly available news articles.

Methods:

We conducted a media content analysis of open-source news coverage on COVID-19 published between January 2020 and June 2022. A dataset of 3,299,158 English news articles on COVID-19 was extracted from the WHO Epidemic Intelligence through Open Sources (EIOS) system. Filtering reduced the number to 7,674 records pertaining to five pre-specified topics. A fine-tuned pre-trained Bidirectional Encoder Representations from Transformers (BERT) model was used to generate topic-focused text summarization of each news article, reducing the dataset word count from 4,629,750 words to 754,619 words. The deductive-inductive approach was used for the analysis of the content of summarizations.

Results:

Media content analysis suggests that insufficient remuneration and compensation packages have been key disruptors for health and care workers during the COVID-19 pandemic, leading to industrial actions and mental health burdens. Shortages of Personal protective equipment (PPE) and occupational risks have increased infection and death risks, particularly at the pandemic's onset. Workload fatigue and staff shortages were a growing disruption as the pandemic progressed.

Conclusions:

This study demonstrates the capacity of AI-assisted analysis applied to openly accessible news articles concerning the health workforce. Adequate remuneration packages and PPE supplies should be prioritized as preventive measures to reduce the initial impact of future pandemics on health and care workers. Interventions aimed at lessening the emotional toll and workload need to be formulated as a part of reactive measures, enhancing the efficiency, and sustainability of healthcare delivery during a pandemic.