Domain Adaptive Fake News Detection via Reinforcement Learning

TL;DR

This paper introduces REAL-FND, a reinforcement learning-based model that leverages auxiliary information to improve fake news detection across diverse domains, especially with limited labeled data.

Contribution

It proposes a novel reinforcement learning framework that incorporates auxiliary data for robust cross-domain fake news detection, addressing annotation cost issues.

Findings

Effective in cross-domain scenarios

Performs well with limited labeled data

Outperforms existing models in experiments

Abstract

With social media being a major force in information consumption, accelerated propagation of fake news has presented new challenges for platforms to distinguish between legitimate and fake news. Effective fake news detection is a non-trivial task due to the diverse nature of news domains and expensive annotation costs. In this work, we address the limitations of existing automated fake news detection models by incorporating auxiliary information (e.g., user comments and user-news interactions) into a novel reinforcement learning-based model called \textbf{RE}inforced \textbf{A}daptive \textbf{L}earning \textbf{F}ake \textbf{N}ews \textbf{D}etection (REAL-FND). REAL-FND exploits cross-domain and within-domain knowledge that makes it robust in a target domain, despite being trained in a different source domain. Extensive experiments on real-world datasets illustrate the effectiveness of the proposed model, especially when limited labeled data is available in the target domain.