Tweet Topic Classification Metrics for COVID-19 Polarization in the US and Canada, 2020

A dataset containing classification metrics for over 50 million tweets from late 2020, analyzing partisan polarization around COVID 19 health interventions. The data was created by Zachary Yang and examines discussions on lockdowns, masks, and vaccines across the United States and Canada. It was last updated on April 20, 2026.

Use Cases

• Analyzing regional variation in partisan polarization based on discussions of lockdowns, masks, and vaccines.
• Investigating the correlation between online polarization and real-world vaccination rates.
• Tracking temporal spikes in polarization linked to specific political events and policy announcements.
• Comparing cross-national differences in polarization dynamics between the United States and Canada.

Strengths

• Based on a large corpus of over 50 million tweets.
• Focuses on a critical period of polarizing discourse during the COVID-19 pandemic in late 2020.
• Provides a cross-national comparison between the United States and Canada.
• Released under a permissive CC-BY-4.0 license.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The 5.5 KB file size suggests the dataset contains summary metrics, not the raw tweet data.

Provenance

Source

figshare

Collection Method

Computational analysis of Twitter data.

Time Range

Late 2020

Freshness

Last updated 2026-04-20 17:58:08; freshness should be verified.

Geography

United States and Canada