Cross-lingual Transfer Learning for Fake News Detector in a Low-Resource Language
This addresses fake news detection for low-resource language communities, but it is incremental as it builds on existing cross-lingual transfer methods.
The study tackled fake news detection in low-resource languages by using training data only from a high-resource language, achieving 3.71% higher accuracy than using machine-translated data and a 3.03% improvement from cross-lingual feature exploitation.
Development of methods to detect fake news (FN) in low-resource languages has been impeded by a lack of training data. In this study, we solve the problem by using only training data from a high-resource language. Our FN-detection system permitted this strategy by applying adversarial learning that transfers the detection knowledge through languages. To assist the knowledge transfer, our system judges the reliability of articles by exploiting source information, which is a cross-lingual feature that represents the credibility of the speaker. In experiments, our system got 3.71% higher accuracy than a system that uses a machine-translated training dataset. In addition, our suggested cross-lingual feature exploitation for fake news detection improved accuracy by 3.03%.