The Role of Partisan Culture in Mental Health Language Online

TL;DR

This study investigates how partisan culture influences expressions of distress in online mental health communities, revealing significant differences between Republican and Democrat users over a decade.

Contribution

It introduces a large-scale, causal inference-based analysis of partisan differences in mental health language using natural language processing.

Findings

Partisan culture affects how users express distress online.

Republican and Democrat users show distinct linguistic patterns.

Partisan differences are significant over the studied period.

Abstract

The impact of culture on how people express distress in online support communities is increasingly a topic of interest within Computer Supported Cooperative Work (CSCW) and Human-Computer Interaction (HCI). In the United States, distinct cultures have emerged from each of the two dominant political parties, forming a primary lens by which people navigate online and offline worlds. We examine whether partisan culture may play a role in how U.S. Republican and Democrat users of online mental health support communities express distress. We present a large-scale observational study of 2,184,356 posts from 8,916 statistically matched Republican, Democrat, and unaffiliated online support community members. We utilize methods from causal inference to statistically match partisan users along covariates that correspond with demographic attributes and platform use, in order to create comparable cohorts for analysis. We then leverage methods from natural language processing to understand how partisan expressions of distress compare between these sets of closely matched opposing partisans, and between closely matched partisans and typical support community members. Our data spans January 2013 to December 2022, a period of both rising political polarization and mental health concerns. We find that partisan culture does play into expressions of distress, underscoring the importance of considering partisan cultural differences in the design of online support community platforms.