Background The COVID-19 pandemic has spotlighted the politicization of public health issues. A public health monitoring tool must be equipped to reveal a public health measure’s political context and guide better interventions. In its current form, infoveillance tends to neglect identity and interest-based users, hence being limited in exposing how public health discourse varies by different political groups. Adopting an algorithmic tool to classify users and their short social media texts might remedy that limitation. Objective We aimed to implement a new computational framework to investigate discourses and temporal changes in topics unique to different user clusters. The framework was developed to contextualize how web-based public health discourse varies by identity and interest-based user clusters. We used masks and mask wearing during the early stage of the COVID-19 pandemic in the English-speaking world as a case study to illustrate the application of the framework. Methods We first clustered Twitter users based on their identities and interests as expressed through Twitter bio pages. Exploratory text network analysis reveals salient political, social, and professional identities of various user clusters. It then uses BERT Topic modeling to identify topics by the user clusters. It reveals how web-based discourse has shifted over time and varied by 4 user clusters: conservative, progressive, general public, and public health professionals. Results This study demonstrated the importance of a priori user classification and longitudinal topical trends in understanding the political context of web-based public health discourse. The framework reveals that the political groups and the 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 with China were found to drive the discourse. It also shows limited participation of public health professionals compared with other users. Conclusions We conclude by discussing the importance of a priori user classification in analyzing web-based discourse and illustrating the fit of BERT Topic modeling in identifying contextualized topics in short social media texts.