Identifying fake news is a very difficult task, especially when considering the multiple modes of conveying information through text, image, video and/or audio. We attempted to tackle the problem of automated misinformation/disinformation detection in multi-modal news sources (including text and images) through our simple, yet effective, approach in the FACTIFY shared task at De-Factify@AAAI2022. Our model produced an F1-weighted score of 74.807%, which was the fourth best out of all the submissions. In this paper we will explain our approach to undertake the shared task.
@article{arxiv.2203.07990,
title = {UofA-Truth at Factify 2022 : Transformer And Transfer Learning Based Multi-Modal Fact-Checking},
author = {Abhishek Dhankar and Osmar R. Zaïane and Francois Bolduc},
journal= {arXiv preprint arXiv:2203.07990},
year = {2022}
}