Enhancing Fake-News Detection with Node-Level Topological Features

TL;DR

This paper enhances fake-news detection by explicitly incorporating classical topological features into node representations, significantly improving performance and interpretability in misinformation identification tasks.

Contribution

It introduces a simple method to fuse explicit topological graph metrics with existing embeddings, boosting detection accuracy and providing interpretability.

Findings

Macro F1 score improved from 0.7753 to 0.8344

Explicit topology features enhance detection performance

Provides a reproducible template for other diffusion tasks

Abstract

In recent years, the proliferation of misinformation and fake news has posed serious threats to individuals and society, spurring intense research into automated detection methods. Previous work showed that integrating content, user preferences, and propagation structure achieves strong performance, but leaves all graph-level representation learning entirely to the GNN, hiding any explicit topological cues. To close this gap, we introduce a lightweight enhancement: for each node, we append two classical graph-theoretic metrics, degree centrality and local clustering coefficient, to its original BERT and profile embeddings, thus explicitly flagging the roles of hub and community. In the UPFD Politifact subset, this simple modification boosts macro F1 from 0.7753 to 0.8344 over the original baseline. Our study not only demonstrates the practical value of explicit topology features in fake-news detection but also provides an interpretable, easily reproducible template for fusing graph metrics in other information-diffusion tasks.