Performance Comparison of Gradient Boosting and Random Forest for the Classification of False News

The rapid increase in the utilization of social media for news browsing is attributed to its capacity, affordability, improved attractiveness, and accessibility, leading to the dissemination of "fake news." The widespread propagation of fake news has unintended negative effects on individuals and culture. Certain individuals exploit social media platforms to disseminate false information, seeking attention and reaping monetary and political advantages. To effectively distinguish between authentic and false news, intelligent solutions are required. The Gradient Boosting Classifier and Random Forest Classifier are the two ML classifiers that we compare and contrast in this research work. In comparison, the Gradient Boosting Classifier outperforms the Random Forest Classifier, achieving an impressive accuracy of 92% in classifying fake news.