Canadian User Party Affiliation Classification from COVID-19 Twitter Discourse

A study by Zachary Yang analyzes over 50 million tweets from late 2020 to measure partisan polarization in discussions about COVID-19 health interventions like lockdowns, masks, and vaccines across the United States and Canada. The dataset, last updated in April 2026, likely contains derived metrics for classifying user party affiliation and quantifying polarization. It explores the relationship between online discourse, regional vaccination rates, and political events.

Use Cases

• Classify Twitter user political affiliation based on discourse patterns mentioned in the description
• Analyze temporal spikes in partisan polarization linked to specific policy announcements
• Compare cross-national polarization dynamics between the U.S. and Canada regarding health measures
• Investigate correlations between regional online polarization and real-world vaccination rates

Strengths

• Based on a large corpus of over 50 million tweets
• Focuses on a critical, well-defined period of discourse in late 2020
• Explicitly compares dynamics across two countries (U.S. and Canada)
• Released under a permissive CC-BY-4.0 license

Limitations

• Row count is unknown, which may limit suitability assessment
• Column-level documentation is absent; field semantics must be inferred after download
• Data reflects bias inherent to Twitter users, who are a politically engaged subset of the population

Provenance

Source

figshare, author Zachary Yang

Collection Method

Computational analysis of Twitter data

Time Range

Late 2020

Freshness

Last updated 2026-04-20 17:58:11; freshness should be verified

Geography

United States and Canada