Automatic detection of fake tweets about COVID-19 Vaccine in Portuguese

The COVID-19 pandemic induced an unprecedented wave of of disinformation in social media in Brazil. In particular Twitter (currently X) was used to spread fake news about COVID-19 vaccines that helped to induce vaccine hesitation.This article presents a BERT-based neural network for automatic detection of fake tweets.The optimized architecture relies upon BERTimbau, a BERT implementation pre-trained in Brazilian Portuguese, fine-tuned using three fully connected layers.All 2,857,908 tweets in Portuguese containing the word \textit{vacina} (vaccine in Portuguese) were collected over a 7-month period.A subset of 14,400 tweets was manually classified as real or fake.The network was fine-tuned using the 1,144 curated fake tweets and a random sample of 2000 real tweets.Optimal results were achieved melting the last four layers of the BERTimbau.The best results obtained were 77.1\% f1-score and 76.9\% accuracy.These results are already acceptable for practical applications.They can be improved increasing the size of the training dataset.State of the art performance was obtained training the same neural network architecture with a larger curated balanced English language training dataset.