g2tmn at Constraint@AAAI2021: Exploiting CT-BERT and Ensembling Learning for COVID-19 Fake News Detection

TL;DR

This paper presents an ensemble transformer-based approach using CT-BERT models for COVID-19 fake news detection, achieving top performance in a shared task with a 98.69 F1-score.

Contribution

The authors develop a novel ensemble method with CT-BERT for fake news detection, incorporating text preprocessing and data augmentation, and demonstrate state-of-the-art results.

Findings

Achieved 98.69 weighted F1-score on test set

Outperformed 165 competing teams in the shared task

Validated effectiveness of ensemble CT-BERT models

Abstract

The COVID-19 pandemic has had a huge impact on various areas of human life. Hence, the coronavirus pandemic and its consequences are being actively discussed on social media. However, not all social media posts are truthful. Many of them spread fake news that cause panic among readers, misinform people and thus exacerbate the effect of the pandemic. In this paper, we present our results at the Constraint@AAAI2021 Shared Task: COVID-19 Fake News Detection in English. In particular, we propose our approach using the transformer-based ensemble of COVID-Twitter-BERT (CT-BERT) models. We describe the models used, the ways of text preprocessing and adding extra data. As a result, our best model achieved the weighted F1-score of 98.69 on the test set (the first place in the leaderboard) of this shared task that attracted 166 submitted teams in total.