Fighting the COVID-19 Infodemic with a Holistic BERT Ensemble

TL;DR

This paper presents TOKOFOU, an ensemble of six transformer models fine-tuned for COVID-19 misinformation detection, achieving top performance with an F1 score of 89.7% in the shared task.

Contribution

It introduces a novel ensemble approach combining multiple transformer encoders for misinformation detection in the COVID-19 context.

Findings

Achieved an F1 score of 89.7%

Ranked first in the shared task

Effective ensemble method for misinformation detection

Abstract

This paper describes the TOKOFOU system, an ensemble model for misinformation detection tasks based on six different transformer-based pre-trained encoders, implemented in the context of the COVID-19 Infodemic Shared Task for English. We fine tune each model on each of the task's questions and aggregate their prediction scores using a majority voting approach. TOKOFOU obtains an overall F1 score of 89.7%, ranking first.