Abstract

Given the prevalence of fake news in today’s tech-driven era, an urgent need exists for an automated mechanism to effectively curb its dissemination. This research aims to demonstrate the impacts of fake news through a literature review and establish a reliable system for identifying it using machine (ML) learning classifiers. By combining CNN, RNN, and ANN models, a novel model is proposed to detect fake news with 94.5% accuracy. Prior studies have successfully employed ML algorithms to identify false information by analysing textual and visual features in standard datasets. The comprehensive literature review emphasises the consequences of fake news on individuals, economies, societies, politics, and free expression. The proposed hybrid model, trained on extensive data and evaluated using accuracy, precision and recall measures, outperforms existing models. This study underscores the importance of developing automated systems to counter the spread of fake news and calls for further research in this domain.