Ensembling of Various Transformer Based Models for the Fake News Detection Task in the Urdu Language

Abstract

The spread of misinformation has become a severe issue affecting society. Inaccurate information has enormous potential to cause real-world impacts. Developing algorithms to detect fake news automatically will be very useful in preventing unnecessary panic and damage caused by rumors. This fake news problem is present for all languages, and it becomes crucial to solve it for languages other than English, with scarce datasets. This paper aims to tackle the problem of automatic fake news detection in Urdu, a low-resource language. FIRE-2021 has provided the Urdu dataset used in this paper. We fine-tuned monolingual and multilingual transformers. After searching for hyperparameters, we tried ensembling our models. We submitted our model for the UrduFake task, and it achieved an accuracy of 0.596 and an F1- macro score of 0.449.