UIJRT » United International Journal for Research & Technology

COVID-19 Fake News Detection Using Naïve Bayes Classifier

PAPER DETAILS

CITE THIS

O. Akande, G. Egwuonwu, and W. Ajayi, 2021. COVID-19 Fake News Detection Using Naïve Bayes Classifier. United International Journal for Research & Technology (UIJRT), 2(12), pp.47-49.

Abstract

This study aimed at detecting fake information relating to COVID-19 using Naïve Bayes. The advent of social media which is made available through the internet provides platforms on which news can be disseminated and reach a large number of audiences in seconds. This opportunity comes with its challenges, of which one major one is the possibility of spreading fake news quickly. Detection of fake news is a binary classification problem that is handled with machine learning techniques that learn on their own. Naive Bayes is one of the well-known machine learning classifiers that is used in resolving text classification problems. This algorithm is applicable regardless of the number of inputs. It was used in this work to build a model which can distinguish fake news from real ones. For the moderately-sized COVID-19 dataset, an accuracy of 96.7% was achieved. With a very large dataset Multimodal, Naïve Bayes will perform better.

Keywords: Algorithm, COVID-19, Fake News, Machine Learning, Naïve Bayes.

Related Papers

For Conference & Paper Publication​