Unseen Fake News Detection Through Casual Debiasing
This addresses the challenge of detecting novel fake news on social media, which is an incremental improvement over existing methods that struggle with unseen news.
The paper tackles the problem of detecting unseen fake news by addressing biases in training data tied to specific domains, proposing a debiasing solution called FNDCD that improves generalization across domains in experiments on real-world datasets.
The widespread dissemination of fake news on social media poses significant risks, necessitating timely and accurate detection. However, existing methods struggle with unseen news due to their reliance on training data from past events and domains, leaving the challenge of detecting novel fake news largely unresolved. To address this, we identify biases in training data tied to specific domains and propose a debiasing solution FNDCD. Originating from causal analysis, FNDCD employs a reweighting strategy based on classification confidence and propagation structure regularization to reduce the influence of domain-specific biases, enhancing the detection of unseen fake news. Experiments on real-world datasets with non-overlapping news domains demonstrate FNDCD's effectiveness in improving generalization across domains.