A Novel Method for COVID-19 Pandemic Information Fake News Detection Based on the Arithmetic Optimization Algorithm

• Published in: 2021 23rd International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC) pp. 259 - 266
• Main Authors: Zivkovic, Miodrag, Stoean, Catalin, Petrovic, Aleksandar, Bacanin, Nebojsa, Strumberger, Ivana, Zivkovic, Tamara
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2021
• Subjects: arithmetic optimization; Classification algorithms; COVID-19; Fake news; Feature extraction; metaheuristics; optimization; Pandemics; Support vector machines; swarm intelligence; Vaccines
• DOI: 10.1109/SYNASC54541.2021.00051

The problem of fake news on the Internet is not new. However, in the case of a global pandemic, this kind of misinformation can be dangerous, confusing, and costly in terms of the loss of human lives. The ongoing COVID-19 pandemic has unfortunately shown the significant and remarkable spread of fake news, concerning the disease itself, vaccination, number of deaths, and so on. It is necessary to develop an effective algorithm that will be able to detect COVID-19 misinformation and help scientists to easily separate fake from true news. The research presented in this paper proposes an arithmetic optimization algorithm (AOA) - based approach that can improve the classification results by reducing the number of features and achieve high accuracy. The AOA has been utilized as a wrapper feature selection. The obtained simulation results were subject to a comparative analysis with both world-class classifiers and other nature-inspired evolutionary approaches. The results of the simulation indicate better performance of the proposed approach with AOA over other algorithms and demonstrate that it obtains superior accuracy.