Truth with a Twist: The Rhetoric of Persuasion in Professional vs. Community-Authored Fact-Checks

TL;DR

The paper investigates whether crowdsourced Community Notes differ from professional debunks in their use of persuasive language. It leverages three large datasets—Community Notes (CNs), EUvsDisinfo, and the Database of Known Fakes (DBKF)—and a multilingual 23-technique persuasion classifier to quantify prevalence, employing Spearman correlation, Mann-Whitney U tests, Cliff's delta, and one-sided z-tests to compare across datasets. It finds no evidence that CNs contain more persuasion techniques on average than professional debunks, but reveals domain- and editorial-norm dependent patterns across datasets, with nuanced per-technique effects. It also shows that crowd raters penalize certain tactics (e.g., Flag-Waving, Guilt by Association, Straw Man) while perceiving others as increasing helpfulness, highlighting the limits and selective effectiveness of CNs’ self-regulation. The work informs understanding of crowd-based content governance, editorial norms, and the practical constraints of moderation in misinformation ecosystems.

Abstract

This study presents the first large-scale comparison of persuasion techniques present in crowd- versus professionally-written debunks. Using extensive datasets from Community Notes (CNs), EUvsDisinfo, and the Database of Known Fakes (DBKF), we quantify the prevalence and types of persuasion techniques across these fact-checking ecosystems. Contrary to prior hypothesis that community-produced debunks rely more heavily on subjective or persuasive wording, we find no evidence that CNs contain a higher average number of persuasion techniques than professional fact-checks. We additionally identify systematic rhetorical differences between CNs and professional debunking efforts, reflecting differences in institutional norms and topical coverage. Finally, we examine how the crowd evaluates persuasive language in CNs and show that, although notes with more persuasive elements receive slightly higher overall helpfulness ratings, crowd raters are effective at penalising the use of particular problematic rhetorical means