Fig 1.
Overview of estimating partisan polarization over date, region and topic.
Using a predefined set of political keywords, we extract and embed tweets, geolocate users, and classify them by party affiliation. Tweets are then categorized by key topic (lockdowns, masks, and vaccines) allowing us to measure partisan polarization over time (daily) and across regions (weekly) in both Canada and the U.S.
Table 1.
Tweet topic classification metrics.
Table 2.
Geolocated users number and correlation.
Table 3.
American user party affiliation classification.
Table 4.
Canadian user party affiliation classification.
Table 5.
Canadian user party affiliation activity classifier confusion matrix.
Table 6.
Canadian user party affiliation activity classifier confusion matrix.
Fig 2.
Normalized distribution of the inferred user party affiliations compared to the Canadian 2021 election results.
A: Canadian 2021 election results. B: Geolocated users. C: Lockdown. D: Mask. E: Vaccine. F: Conspiracy.
Fig 3.
Empirical distribution of the inferred user party affiliations compared to the US 2020 election results.
Interestingly, lockdown matches closer to the election results, mask and vaccine has a higher liberal ratio and conspiracy has a higher conservative ratio. A: Canadian 2021 election results. B: Geolocated users. C: Lockdown. D: Mask. E: Vaccine. F: Conspiracy.
Table 7.
Users matched to their voter registration.
Fig 4.
Approximation of poli: Error and Runtime Tradeoff.
A: Approximation quality. For large enough data, the approximation error is close to 0.001.B: Time saved in seconds. Our approximation of polarization also exponentially saves time as the number of instances grows. For both panels, we plot the mean and standard deviation over 10 independent runs across different minimum coefficients of variation (CV).
Fig 5.
Approximation of poli: Effect of Minimum Coefficient of Variation.
Green dots mean time was saved while red means time lost. The circle size is the absolute error times 1000. The inner plot zooms in and doubles the circle sizes for clarity. We observe that the fraction of instances needed increase as we decrease the needed minimum coefficient of variation. This follows our intuition as a larger sample of data is much easier to approximate the full data. We also that at lower minimum coefficient of variation, the less error we have (circles are much smaller). On all plots, we also see that we always save time (green circles) if there are more than 10,000 instances.
Fig 6.
Approximation of poli: Effect of Repeat Count.
As in the preceding figure, we observe that as we increase the number of repeats, the less error we have in our approximation (smaller circles). Likewise the amount of time saved decreases as we increase the repeat count (amount of red circles increase as repeats increase). We also observe a general slight increase in the fraction of instances needed as we increase the repeats.
Fig 7.
Regional distribution of partisan polarization in the United States.
A: Lockdown. B: Mask. C: Vaccine. D: % of conspiracy-related tweets. Color intensity from light to dark gives the amount of polarization measured weekly between October 11, 2020 to January 3, 2021 and then averaged over the 12 weeks. We also report the average weekly percentage of conspiracy-related tweets that are posted from users in each region in panel (D).
Fig 8.
Regional distribution of partisan polarization in Canada.
A: Lockdown. B: Mask. C: Vaccine. D: % of conspiracy-related tweets. The polarization is measured weekly between October 11, 2020 to January 3, 2021 and the averaged over 12 weeks is used for this plot. We also report the average weekly percentage of conspiracy-related tweets that are posted from users in each region Provinces and territory boundaries are colored based on the number of users we had in our data from those regions, which indicates the support for our measurement: Light-grey for less than 100 users, grey for between 100 and 1,000 users and black for greater than 1,000 users.
Fig 9.
Ranking of American states partisan polarization per topic and overall.
Ranking of 1 signifies the highest average weekly polarization between October 11, 2020 to January 3, 2021 (12 weeks). State names are colored according to the colorbar (red to blue), based on the vote margin for the conservative party from the 2020 United States Presidential Election (Conservative Party: Republican Party; Liberal Party: Democratic Party).
Fig 10.
Partisan polarization ranking of Canadian provinces and territories per topic and overall.
A ranking of 1 signifies the highest average weekly polarization between October 11, 2020 to January 3, 2021 (12 weeks). Province or territory names are colored (red to blue) based on the vote margin for the conservative party family from Canada’s 2019 Federal Election (Liberal Party Family: Liberal, New Democratic Party, Green; Conservative Party Family: Conservative, People’s Party). Line colors have a transparency to reflect the support for the measurement, based on the number of users in that region.
Fig 11.
Correlation between polarization score and vote margin for the conservative party.
Colors (blue to red) are conservative party vote margin (same as Fig 9 and Fig 10). Significant correlation between Polarization Score and Vote Margin is found for the US discourse on masks and on vaccines for which the respective Pearson r correlation and p-value is shown.
Fig 12.
Relation between vaccines polarization and vaccination rates in the United States.
Color (blue to red) is again the respective conservative party vote margin from the 2020 U.S. Presidential Election. The correlation is −0.77 with CI = [−0.86, −0.62] (n = 51, p = 6.97e-11).
Table 8.
Major political and pandemic-related events in each country.
Table 9.
US polarization peaks and their corresponding events.
Table 10.
Canadian polarization peaks and their corresponding events.
Fig 13.
Daily trends of partisan polarization in the United States and Canada from October 9, 2020 to January 3, 2021.
A: US Daily Lockdown Polarization. B: Canadian Daily Lockdown Polarization. C: US Daily Mask Polarization. D: Canadian Daily Lockdown Polarization. E: US Daily Vaccine Polarization. F: Canadian Daily Vaccine Polarization. The vertical dashed lines denote pre-selected political and vaccine-related events as explained in the text. In addition to the polarization measure (purple line), we also report the tweet volume, in log-scale, on the corresponding topic (yellow line) per day which denotes the size of support for our measurement.
Fig 14.
Daily aggregated partisan polarization.
For the U.S. (A, B) and Canada (C, D), polarization is aggregated over topic by averaging over the values. We show pandemic-related new cases and deaths in background for reference. Event-triggered average polarization for identified events are listed in Table 9 and Table 10 respectively. Shaded region denotes standard deviation over the 5 events for each country.
Fig 15.
Relation between the volume of conspiracy related content and the observed partisan polarization in the United States and Canada.
In the left column, we report the volume of conspiracy related tweets posted by users for the United States (A: affiliated with the Democrat and Republican party) and Canada (C: affiliated with the liberal (left) Party Family (LPF)—Liberal, New Democratic Party, Green, and the conservative (right) Party Family (RPF)—Conservative, People’s Party for Canada). On the right, we show the relation between daily partisan polarization summed over the different topics and the overall volume of conspiracy tweets. In the United States (B), we find there is a statistically significant correlation −0.247 with CI=[−0.448,-0.023] (n = 88, p = 0.031) between these measures. In Canada (D), we find that there is no statistically significant correlation of 0.023 with CI=[−0.187,0.231] (n = 88, p = 0.831) between these measures.