Memory-Guided Multi-View Multi-Domain Fake News Detection

TL;DR

This paper introduces M$^3$FEND, a novel framework that leverages memory-guided multi-view modeling to improve multi-domain fake news detection, effectively addressing domain shift and labeling issues across diverse news topics.

Contribution

It proposes a memory-guided multi-view framework with a domain memory bank and adapter to enhance multi-domain fake news detection, handling domain shift and incomplete labels.

Findings

Outperforms existing methods on English and Chinese datasets.

Effectively models semantics, emotion, and style for better detection.

Demonstrates practical superiority through online testing.

Abstract

The wide spread of fake news is increasingly threatening both individuals and society. Great efforts have been made for automatic fake news detection on a single domain (e.g., politics). However, correlations exist commonly across multiple news domains, and thus it is promising to simultaneously detect fake news of multiple domains. Based on our analysis, we pose two challenges in multi-domain fake news detection: 1) domain shift, caused by the discrepancy among domains in terms of words, emotions, styles, etc. 2) domain labeling incompleteness, stemming from the real-world categorization that only outputs one single domain label, regardless of topic diversity of a news piece. In this paper, we propose a Memory-guided Multi-view Multi-domain Fake News Detection Framework (M$^3$FEND) to address these two challenges. We model news pieces from a multi-view perspective, including semantics, emotion, and style. Specifically, we propose a Domain Memory Bank to enrich domain information which could discover potential domain labels based on seen news pieces and model domain characteristics. Then, with enriched domain information as input, a Domain Adapter could adaptively aggregate discriminative information from multiple views for news in various domains. Extensive offline experiments on English and Chinese datasets demonstrate the effectiveness of M$^3$FEND, and online tests verify its superiority in practice. Our code is available at https://github.com/ICTMCG/M3FEND.