Enriching GNNs with Text Contextual Representations for Detecting Disinformation Campaigns on Social Media

TL;DR

This paper enhances Graph Neural Networks for disinformation detection on social media by integrating Transformer-based textual features, resulting in significant performance improvements and offering insights into feature sources and data noise effects.

Contribution

It introduces the use of Transformer-based contextual text representations within GNNs for fake news detection, surpassing previous static text methods.

Findings

33.8% relative improvement in Macro F1 over models without textual features

9.3% improvement over static text representations

Insights into feature source impacts and noisy data effects

Abstract

Disinformation on social media poses both societal and technical challenges, requiring robust detection systems. While previous studies have integrated textual information into propagation networks, they have yet to fully leverage the advancements in Transformer-based language models for high-quality contextual text representations. This work addresses this gap by incorporating Transformer-based textual features into Graph Neural Networks (GNNs) for fake news detection. We demonstrate that contextual text representations enhance GNN performance, achieving 33.8% relative improvement in Macro F1 over models without textual features and 9.3% over static text representations. We further investigate the impact of different feature sources and the effects of noisy data augmentation. We expect our methodology to open avenues for further research, and we made code publicly available.