An Emotion-guided Approach to Domain Adaptive Fake News Detection using Adversarial Learning

TL;DR

This paper introduces an emotion-guided, domain-adaptive multi-task approach for fake news detection, demonstrating its effectiveness across different datasets and addressing the challenge of cross-domain generalization.

Contribution

It presents a novel emotion-guided, adversarial learning framework for domain adaptation in fake news detection, which is a new approach in this research area.

Findings

Emotion-guided models improve cross-domain fake news detection performance.

The proposed method outperforms baseline models on multiple datasets.

Emotion features enhance the robustness of fake news classifiers.

Abstract

Recent works on fake news detection have shown the efficacy of using emotions as a feature for improved performance. However, the cross-domain impact of emotion-guided features for fake news detection still remains an open problem. In this work, we propose an emotion-guided, domain-adaptive, multi-task approach for cross-domain fake news detection, proving the efficacy of emotion-guided models in cross-domain settings for various datasets.