Research Summary: Fake News Theories: Harnessing Disciplinary Insights for Computational Modeling, Detection, and Explanation

Research is addressing the limitations of existing automated fake news detection systems, which often lack interpretability and strong connections to established theories of persuasion and human judgment. A new computational framework is being developed to translate cross-disciplinary theories from social sciences, psychology, and economics into measurable features, aiming to enhance the accuracy and explanatory power of detection methods through statistical techniques and large language models.

Why it matters

This research is critical for improving the robustness and trustworthiness of automated disinformation detection systems. By grounding computational models in established theories, it enhances their ability not only to identify fake news but also to explain its mechanisms of influence, which is vital for developing effective countermeasures.

Key insights

• Current automated fake news detectors, despite increasing accuracy, often lack interpretability.
• Many existing detection systems are weakly connected to established theories of persuasion, credibility, and human judgment.
• A theory-informed computational framework is being developed to bridge this gap.
• The framework translates cross-disciplinary theories into measurable features for automated detection and explanation.
• Statistical techniques and large language models are central to this computational approach.
• The research involves a structured review of theories from social sciences, psychology, and economics to understand how fake news persuades and spreads.

Source

arXiv — Computers and Society — https://arxiv.org/abs/2609.30427