MATHEMATICAL MODELING OF FAKE NEWS SPREAD MACHINE LEARNING DYNAMICS

Fake news has spread more quickly thanks to social media's explosive growth, which has had serious social and political repercussions. The majority of current methods concentrate on identifying false information after it has spread rather than examining its dynamic propagation behavior. This study suggests a mathematical modeling framework for the spread of fake news that incorporates dynamic analysis based on machine learning. In order to depict users as susceptible, infected, and recovered states within a social network, the model modifies the principles of epidemic propagation. The spread dynamics are described by differential equations, and machine learning classifiers help detect fraudulent content and modify transition parameters. According to simulation results, combining machine learning and mathematical modeling enhances prediction accuracy and supports efficient misinformation control techniques. The suggested framework offers an organized method for comprehending and reducing the spread of false information in digital communication networks,