JMIR Publications

ABSTRACT

Background:

Nurse stories about their experiences during the COVID-19 pandemic offer significant opportunities for healthcare organizations to understand how their primary caregivers are affected by external pressures and internal managerial decisions.

Objective:

The objective of this study is to examine the evolution of nurses’ work concerns during the COVID-19 pandemic using conversations posted by nursing professionals in social media.

Methods:

We analyzed 14,060 posts related to the COVID-19 pandemic from March 2020 to April 2021. The data analysis stage included unsupervised machine learning and thematic qualitative analysis. We used an unsupervised machine learning approach, Latent Dirichlet Allocation (LDA) to identify salient topics in the collected posts. A human-in-the-loop (HITL) analysis complemented the machine learning approach, categorizing topics into themes and sub-themes. We develop insights on nurses’ evolving perspective based on temporal changes.

Results:

We identified themes for bi-weekly periods and grouped them into 20 major themes based on the work concerns inventory framework. Dominant work concerns varied during the specific time period. A detailed analysis of patterns in how themes evolve over time enables us to create narratives of work concerns.

Conclusions:

This study showed that online conversation data and machine learning approaches can enable research into work concerns and workplace stressors during the COVID-19 pandemic. The study shows that monitoring and assessment of online discussions could provide useful data for healthcare organizations responses and planning during crises.