LLM-based Contrastive Self-Supervised AMR Learning with Masked Graph Autoencoders for Fake News Detection

TL;DR

This paper introduces a self-supervised framework for fake news detection that combines semantic understanding via AMR, social propagation dynamics, and LLM-based contrastive learning to improve accuracy with limited labeled data.

Contribution

It presents a novel self-supervised approach integrating AMR, social context, and LLM-based contrastive loss for fake news detection, reducing reliance on labeled datasets.

Findings

Outperforms state-of-the-art methods in limited labeled data scenarios.

Effectively captures semantic and social propagation features.

Enhances generalizability of fake news detection models.

Abstract

The proliferation of misinformation in the digital age has led to significant societal challenges. Existing approaches often struggle with capturing long-range dependencies, complex semantic relations, and the social dynamics influencing news dissemination. Furthermore, these methods require extensive labelled datasets, making their deployment resource-intensive. In this study, we propose a novel self-supervised misinformation detection framework that integrates both complex semantic relations using Abstract Meaning Representation (AMR) and news propagation dynamics. We introduce an LLM-based graph contrastive loss (LGCL) that utilizes negative anchor points generated by a Large Language Model (LLM) to enhance feature separability in a zero-shot manner. To incorporate social context, we employ a multi view graph masked autoencoder, which learns news propagation features from social context graph. By combining these semantic and propagation-based features, our approach effectively differentiates between fake and real news in a self-supervised manner. Extensive experiments demonstrate that our self-supervised framework achieves superior performance compared to other state-of-the-art methodologies, even with limited labelled datasets while improving generalizability.