An Approach to Detect Fake News Based on Machine Learning

In today's world, the proliferation of internet-connected devices is significantly increasing among users, creating a huge amount of information. It creates a big challenge to reliable information shared through these devices. The reliability of news is important to stop its negative side effects. Several fake news articles are broadcast publicly for the specific creator's small benefits. Therefore, a mechanism to identify such fake news is required so society is not stuck in counterfeit illusions. Nowadays, machine learning-based approaches are the most suitable way to recognize such news. A few researchers use machine learning to enhance the accuracy of predicting fake news. This paper also utilized the machine learning-based method to separate fake news from legitimate news sources. First, we analyze concepts of K-Nearest Neighbor (KNN), Logistic Regression (LR), Support Vector Machines (SVM), and Random Forest (RF) on a few important factors. Then, we propose an ensemble model to accurately identify fake news using counterfeit news detection datasets. The performance of the proposed method is proved through the experimental evaluation of how efficiently the method detects fake news. Finally, the proposed method detection findings are compared with a few important methods, showing the model's effectiveness.