Evaluating Deep Learning Approaches for Covid19 Fake News Detection

TL;DR

This paper evaluates various deep learning models, including CNN, LSTM, and BERT, for detecting Covid-19 fake news, achieving high accuracy and emphasizing the role of unsupervised learning techniques.

Contribution

It compares supervised and unsupervised deep learning methods for Covid-19 fake news detection, highlighting the effectiveness of BERT and pre-training strategies.

Findings

BERT achieved 98.41% accuracy on the dataset.

Unsupervised pre-training improves fake news detection performance.

Deep learning models outperform traditional methods.

Abstract

Social media platforms like Facebook, Twitter, and Instagram have enabled connection and communication on a large scale. It has revolutionized the rate at which information is shared and enhanced its reach. However, another side of the coin dictates an alarming story. These platforms have led to an increase in the creation and spread of fake news. The fake news has not only influenced people in the wrong direction but also claimed human lives. During these critical times of the Covid19 pandemic, it is easy to mislead people and make them believe in fatal information. Therefore it is important to curb fake news at source and prevent it from spreading to a larger audience. We look at automated techniques for fake news detection from a data mining perspective. We evaluate different supervised text classification algorithms on Contraint@AAAI 2021 Covid-19 Fake news detection dataset. The classification algorithms are based on Convolutional Neural Networks (CNN), Long Short Term Memory (LSTM), and Bidirectional Encoder Representations from Transformers (BERT). We also evaluate the importance of unsupervised learning in the form of language model pre-training and distributed word representations using unlabelled covid tweets corpus. We report the best accuracy of 98.41\% on the Covid-19 Fake news detection dataset.