Emotion-guided Cross-domain Fake News Detection using Adversarial Domain Adaptation
This work addresses the problem of domain shift in fake news detection for social media and news platforms, but it is incremental as it builds on existing emotion-based methods.
The paper tackles cross-domain fake news detection by evaluating and proposing emotion-guided features with adversarial domain adaptation, achieving improved performance across multiple dataset combinations.
Recent works on fake news detection have shown the efficacy of using emotions as a feature or emotions-based features for improved performance. However, the impact of these emotion-guided features for fake news detection in cross-domain settings, where we face the problem of domain shift, is still largely unexplored. In this work, we evaluate the impact of emotion-guided features for cross-domain fake news detection, and further propose an emotion-guided, domain-adaptive approach using adversarial learning. We prove the efficacy of emotion-guided models in cross-domain settings for various combinations of source and target datasets from FakeNewsAMT, Celeb, Politifact and Gossipcop datasets.