JMIR Publications

ABSTRACT

Background:

The COVID-19 pandemic has spotlighted the intertwining of politics and public health. So too, a public health tool, surveillance, can also be used to expose an event's political context and guide better public health interventions. In its current form, infoveillance tends to neglect identity and interest-based users. Adopting an algorithmic tool to appropriately classify short social media texts might remedy that gap.

Objective:

We aim to understand the role of political ideologies and political groups in defining the Twitter discourse on masks and mask-wearing during COVID-19 in the English-speaking world. The study uses a new computational framework to investigate discourses and temporal changes of topics unique to different user groups/communities.

Methods:

The study first clusters Twitter users based on their identities and interests as expressed through Twitter bio pages. It then uses BERT topic modeling combined to identify topics by the user clusters. It reveals how online discourse shifted over time and varied by four user clusters: Conservative political, Progressive political, General Public, and Public Health Professionals.

Results:

The political groups and general public focused on the science of mask-wearing and the partisan politics of mask policies. A populist discourse that pits citizens against elites and institutions was identified in some tweets. Politicians (such as Donald Trump) and geopolitical tensions (regarding China) drove the discourse. Our data show limited participation of public health professionals compared to other users.

Conclusions:

We conclude by discussing the importance of a priori user classification in analyzing online discourse and illustrating the fit of BERT topic modeling in identifying contextualized topics in short social media texts.