Angry but Accurate: Detecting and Profiling the Counter-Misinformation Ecosystem on Twitter

Research from arXiv, 'Angry but Accurate: Detecting and Profiling the Counter-Misinformation Ecosystem on Twitter,' challenges common assumptions about online discourse. It finds that posts opposing misinformation on Twitter are often more emotionally negative, expressing higher levels of anger, disgust, and sadness, compared to posts supporting false claims. This finding is based on an analysis of over 260,000 COVID-19 related tweets using a domain-specific Natural Language Inference (NLI) model.

Why it matters

Understanding the emotional characteristics of counter-misinformation efforts is critical for developing effective communication strategies and platform moderation policies. This challenges prevailing assumptions about emotional expression in online discourse, which can inform approaches to fostering healthy digital environments and managing information integrity.

Key insights

• Misinformation-opposing posts on Twitter exhibit higher levels of negative emotion (anger, disgust, sadness) than misinformation-supporting posts.
• The study analyzed 264,737 tweets related to COVID-19, classifying them as supporting or opposing false claims.
• A domain-specific Natural Language Inference (NLI) model was used to categorize posts.
• The research counters the assumption that negative emotion is primarily a characteristic of false information spreaders.

Source

arXiv — Computers and Society — https://arxiv.org/abs/2607.02900