[Paper Review] Capitol (Pat)riots: A comparative study of Twitter and Parler

Hitkul, Avinash Prabhu+10 more|arXiv (Cornell University)|Jan 18, 2021

Misinformation and Its Impacts4 references29 citations

TL;DR

The paper compares trending content, user activity, and traffic organicity on Parler and Twitter during the Capitol riot period, finding pro-riot and misinformation on Parler with manipulated traffic, versus largely condemnatory content on Twitter.

ABSTRACT

On 6 January 2021, a mob of right-wing conservatives stormed the USA Capitol Hill interrupting the session of congress certifying 2020 Presidential election results. Immediately after the start of the event, posts related to the riots started to trend on social media. A social media platform which stood out was a free speech endorsing social media platform Parler; it is being claimed as the platform on which the riots were planned and talked about. Our report presents a contrast between the trending content on Parler and Twitter around the time of riots. We collected data from both platforms based on the trending hashtags and draw comparisons based on what are the topics being talked about, who are the people active on the platforms and how organic is the content generated on the two platforms. While the content trending on Twitter had strong resentments towards the event and called for action against rioters and inciters, Parler content had a strong conservative narrative echoing the ideas of voter fraud similar to the attacking mob. We also find a disproportionately high manipulation of traffic on Parler when compared to Twitter.

Motivation & Objective

• Investigate how Parler and Twitter circulated content about the Capitol riot around Jan 6, 2021.
• Compare topics and hashtags used on both platforms.
• Examine who produced content and who engaged with it on each platform.
• Assess how
• objective

Proposed method

• Collect data from Parler and Twitter during the riot window (Parler: 7–8 Jan 2021; Tweets: 7–8 Jan 2021).
• Identify trending hashtags and keywords to study topics and discourse.
• Quantify topic prevalence via top hashtags and terms analyses.
• Analyze user activity: most active users, mentions, and reposts.
• Assess content organicity using the Coefficient of Traffic Manipulation (CTM) metric.
• Compare user bios and joining dates to profile platform demographics.

Experimental results

Research questions

• RQ1 What topics and hashtags dominated discourse on Parler and Twitter during the Capitol riot period?
• RQ2 Who were the most active users and most mentioned accounts on each platform, and how did engagement differ?
• RQ3 How organic was traffic on Parler compared to Twitter, as measured by CTM?
• RQ4 What distinctions exist in user demographics and bios between Parler and Twitter during this event?
• RQ5 Do the platforms exhibit echo chambers or polarized narratives around the riot?

Key findings

• Parler showed a conservative, pro-riot narrative with misinformed voter-fraud content, while Twitter content largely denounced the riot and urged action against rioters.
• Parler’s top hashtags were present in over 70% of posts, far higher than Twitter’s 12% for its top hashtag, indicating a more one-sided narrative on Parler.
• CTM analysis revealed Parler traffic was disproportionately manipulated, with the highest CTM scores up to 46 times those on Twitter.
• Five Parler users accounted for about 11% of content, suggesting traffic manipulation and concentration of influence.
• On Parler, most mentioned users were right-leaning figures; on Twitter, mentions skewed toward left-leaning leaders and agencies like the FBI.
• Reposts on Parler were dominated by a small set of conservative accounts, indicating an echo-chamber effect, whereas Twitter’s retweets favored left-leaning accounts and organizations.
• Parler bios and joining dates suggested a highly polar, politically active user base, with distinct peaks around major events (e.g., Capitol riot).