Fake News Detection Using Logistic Regression and LightGBM

The spread of false information via fake news in recent years has raised serious issues and caused social discontent and division. It is critical to create efficient techniques for quickly and reliably recognizing bogus news. In the context of identifying fake news, this paper compares two popular machine learning techniques: LightGBM and Logistic Regression. Our analysis makes use of a dataset that includes both fake and real news pieces, with 23,481 fraudulent news stories and 21,417 real news stories. Important performance parameters including recall, accuracy, precision, F1-score, and Matthews correlation coefficient are taken into account while evaluating these algorithms. Our goal in doing this research is to clarify how effective these strategies are at solving the urgent problem of the spread of false information.