CovidMis20: COVID-19 Misinformation Detection System on Twitter Tweets using Deep Learning Models

TL;DR

This paper introduces CovidMis20, a large COVID-19 misinformation dataset from Twitter, and demonstrates deep learning models, including Bi-LSTM and ensemble CNN+Bi-GRU, for detecting fake news with high accuracy.

Contribution

The paper presents a new extensive COVID-19 misinformation dataset and applies deep learning models for effective fake news detection on Twitter.

Findings

Ensemble CNN+Bi-GRU achieved 92.23% accuracy.

Bi-LSTM achieved 90.56% accuracy.

CovidMis20 dataset is publicly available for research.

Abstract

Online news and information sources are convenient and accessible ways to learn about current issues. For instance, more than 300 million people engage with posts on Twitter globally, which provides the possibility to disseminate misleading information. There are numerous cases where violent crimes have been committed due to fake news. This research presents the CovidMis20 dataset (COVID-19 Misinformation 2020 dataset), which consists of 1,375,592 tweets collected from February to July 2020. CovidMis20 can be automatically updated to fetch the latest news and is publicly available at: https://github.com/everythingguy/CovidMis20. This research was conducted using Bi-LSTM deep learning and an ensemble CNN+Bi-GRU for fake news detection. The results showed that, with testing accuracy of 92.23% and 90.56%, respectively, the ensemble CNN+Bi-GRU model consistently provided higher accuracy than the Bi-LSTM model.