Transformers to Fight the COVID-19 Infodemic

TL;DR

This paper presents a transformer-based approach to detect false information related to COVID-19 across three languages, achieving competitive F1 scores and ranking fourth in the NLP4IF-2021 shared task.

Contribution

The paper introduces a transformer-based method for multilingual false information detection in social media tweets during the COVID-19 pandemic.

Findings

Achieved 0.707 F1 in Arabic

Achieved 0.578 F1 in Bulgarian

Achieved 0.864 F1 in English

Abstract

The massive spread of false information on social media has become a global risk especially in a global pandemic situation like COVID-19. False information detection has thus become a surging research topic in recent months. NLP4IF-2021 shared task on fighting the COVID-19 infodemic has been organised to strengthen the research in false information detection where the participants are asked to predict seven different binary labels regarding false information in a tweet. The shared task has been organised in three languages; Arabic, Bulgarian and English. In this paper, we present our approach to tackle the task objective using transformers. Overall, our approach achieves a 0.707 mean F1 score in Arabic, 0.578 mean F1 score in Bulgarian and 0.864 mean F1 score in English ranking 4th place in all the languages.