Exploring Content and Social Connections of Fake News with Explainable Text and Graph Learning

TL;DR

This paper presents an explainable multimodal framework combining content, social, and graph features to improve fact-checking of misinformation across multiple languages, emphasizing interpretability and robustness.

Contribution

It introduces a novel explainable model integrating content, social, and graph data for misinformation detection, enhancing interpretability and cross-lingual performance.

Findings

Multimodal information improves fact-checking accuracy.

The framework provides human-understandable explanations.

Evaluations show high interpretability and robustness.

Abstract

The global spread of misinformation and concerns about content trustworthiness have driven the development of automated fact-checking systems. Since false information often exploits social media dynamics such as "likes" and user networks to amplify its reach, effective solutions must go beyond content analysis to incorporate these factors. Moreover, simply labelling content as false can be ineffective or even reinforce biases such as automation and confirmation bias. This paper proposes an explainable framework that combines content, social media, and graph-based features to enhance fact-checking. It integrates a misinformation classifier with explainability techniques to deliver complete and interpretable insights supporting classification decisions. Experiments demonstrate that multimodal information improves performance over single modalities, with evaluations conducted on datasets in English, Spanish, and Portuguese. Additionally, the framework's explanations were assessed for interpretability, trustworthiness, and robustness with a novel protocol, showing that it effectively generates human-understandable justifications for its predictions.