Unified Fake News Detection using Transfer Learning of Bidirectional Encoder Representation from Transformers model

Automatic detection of fake news is needed for the public as the accessibility of social media platforms has been increasing rapidly. Most of the prior models were designed and validated on individual datasets separately. But the lack of generalization in models might lead to poor performance when deployed in real-world applications since the individual datasets only cover limited subjects and sequence length over the samples. This paper attempts to develop a unified model by combining publicly available datasets to detect fake news samples effectively.