Digital news becomes widely accessible to a large community of users with the advancement of several channels of communication and the progression of technology and thus, contributes to the increase of spreading of fake news. The current study experiments and investigates machine learning models that classify news as either fake or real. Five classifiers were implemented using Random Forest, Support Vector Machine, Gradient Boosting, Logistic Regression, and Naïve Bayes algorithms. Models were trained using merged open-source datasets extracted from online sources covering different domains. Text lemmatization, vectorization, and tokenization were applied to extract useful information from news text and to improve the generalization capabilities and the performance of fake news classification models. The impact of the voting strategy on the performance of ensemble learning models were explored. The performance of the five classifiers was evaluated using the accuracy, the F1-Score, the recall, and the precision. The attained results are promising. The ensemble classifier trained using random forest algorithm and gradient boosting algorithm outperform the other classifiers and thus it might be used effectively against fake news spreading.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.