The rapid advancement of social networks and the convenience of internet availability have accelerated the rampant spread of false news and rumors on social media sites. Amid the COVID 19 epidemic, this misleading information has aggravated the situation by putting peoples mental and physical lives in danger. To limit the spread of such inaccuracies, identifying the fake news from online platforms could be the first and foremost step. In this research, the authors have conducted a comparative analysis by implementing five transformer based models such as BERT, BERT without LSTM, ALBERT, RoBERTa, and a Hybrid of BERT & ALBERT in order to detect the fraudulent news of COVID 19 from the internet. COVID 19 Fake News Dataset has been used for training and testing the models. Among all these models, the RoBERTa model has performed better than other models by obtaining an F1 score of 0.98 in both real and fake classes.

Withtheadventofsocialmedia,therehasbeenanextremely rapid increase in the content shared online. Consequently, the propagation of fake news and hostile messages on social media platforms has also skyrocketed. In this paper, we address the problem of detecting hostile and fake content in the Devanagari (Hindi) script as a multi-class, multi-label problem. Using NLP techniques, we build a model that makes use of an abusive language detector coupled with features extracted via Hindi BERT and Hindi FastText models and metadata. Our model achieves a 0.97 F1 score on coarse grain evaluation on Hostility detection task. Additionally, we built models to identify fake news related to Covid-19 in English tweets. We leverage entity information extracted from the tweets along with textual representations learned from word embeddings and achieve a 0.93 F1 score on the English fake news detection task.

In this paper, we describe our system for the AAAI 2021 shared task of COVID-19 Fake News Detection in English, where we achieved the 3rd position with the weighted F1 score of 0.9859 on the test set. Specifically, we proposed an ensemble method of different pre-trained language models such as BERT, Roberta, Ernie, etc. with various training strategies including warm-up,learning rate schedule and k-fold cross-validation. We also conduct an extensive analysis of the samples that are not correctly classified. The code is available at:https://github.com/archersama/3rd-solution-COVID19-Fake-News-Detection-in-English.