Transfer learning and GRU-CRF augmentation for Covid-19 fake news detection

The spread of fake news on online media is very dangerous and can lead to casualties, effects psychology, character assassination, elections for political parties, state chaos. Fake that concerning Covid-19 massively during the pandemic. Detecting misinformation Internet an essential challenging task since humans face difficulty detecting news. We applied BERT GPT2 as pre-trained using BiGRU-Att-CapsuleNet model BiGRU-CRF features augmentation solve News detection in Constraint @ AAAI2021 - COVID19 Detection English Dataset. This research proved our hybrid with got better accuracy compared baseline model. It also showed gave a result than all models; highest we achieved 0.9196, 0.8986.