Impact of Stricter Content Moderation on Parler's Users' Discourse
Nihal Kumarswamy, Mohit Singhal, Shirin Nilizadeh
TL;DR
The paper investigates how Parler’s post-hiatus, platform-wide moderation changes affected user discourse using a quasi-experimental Difference-in-Differences design with a large longitudinal dataset (17M parleys from 432K users) and Twitter as a control. Toxicity was quantified with the Perspective API, and MBFC was used to assess factuality and bias of shared links, revealing significant reductions in multiple toxicity attributes after moderation, alongside increased link factuality and decreased conspiracy content. The study also documents shifts in user characteristics (more followers/following, more verified/gold badges) and content topics (rise of patriot discourse) and notes cross-platform migration risks to fringe sites. Overall, the work demonstrates the potential effectiveness of platform-wide, progressive moderation policies and provides the first post-relaunch Parler dataset and a framework for evaluating moderation across a platform’s active user base.
Abstract
Social media platforms employ various content moderation techniques to remove harmful, offensive, and hate speech content. The moderation level varies across platforms; even over time, it can evolve in a platform. For example, Parler, a fringe social media platform popular among conservative users, was known to have the least restrictive moderation policies, claiming to have open discussion spaces for their users. However, after linking the 2021 US Capitol Riots and the activity of some groups on Parler, such as QAnon and Proud Boys, on January 12, 2021, Parler was removed from the Apple and Google App Store and suspended from Amazon Cloud hosting service. Parler would have to modify their moderation policies to return to these online stores. After a month of downtime, Parler was back online with a new set of user guidelines, which reflected stricter content moderation, especially regarding the \emph{hate speech} policy. In this paper, we studied the moderation changes performed by Parler and their effect on the toxicity of its content. We collected a large longitudinal Parler dataset with 17M parleys from 432K active users from February 2021 to January 2022, after its return to the Internet and App Store. To the best of our knowledge, this is the first study investigating the effectiveness of content moderation techniques using data-driven approaches and also the first Parler dataset after its brief hiatus. Our quasi-experimental time series analysis indicates that after the change in Parler's moderation, the severe forms of toxicity (above a threshold of 0.5) immediately decreased and sustained. In contrast, the trend did not change for less severe threats and insults (a threshold between 0.5 - 0.7). Finally, we found an increase in the factuality of the news sites being shared, as well as a decrease in the number of conspiracy or pseudoscience sources being shared.