Topic Modeling-Based Analysis of News Keywords Related to Patients with Diabetes during the COVID-19 Pandemic

Abstract

This study analyzed major issues related to diabetes during the coronavirus disease (COVID-19) pandemic by using topic modeling analysis of online news articles provided by BIGKind dating from 20 January 2020, the onset of the COVID-19 outbreak in Korea, to 17 April 2022, the lifting of the social distancing restrictions. We selected 226 articles and conducted topic modeling analysis to identify the main agenda of news related to patients with diabetes in the context of the COVID-19 pandemic; both latent Dirichlet allocation and visualization were conducted by generating keywords extracted from news text as a matrix using Python 3.0. Four main topics were extracted from the news articles related to “COVID-19” and “diabetes” during the COVID-19 pandemic, including “COVID-19 high-risk group,” “health management through digital healthcare,” “risk of metabolic disease related to quarantine policy,” and “child and adolescent obesity and diabetes.” This study is significant because it uses big data related to diabetes that was reported in the mass media during the new epidemic to identify problems in the health management of patients with diabetes during a new epidemic and discuss areas that should be considered for future interventions.