The speed with which fake news and other kinds of misinformation spread on social media platforms is a big problem for modern society. It leads to chaos, and studies have shown that it can change how elections turn out. So, protecting social networks means using tools that can find fake news. In the past few years, there has been a lot of interest in using machine learning, or ML, to spot fake news in the media. This study looks into the different machine learning (ML) approaches and frameworks that can be used to spot fake information spread on social media. In this article, we'll talk about how to spot fake news by using natural language processing (NLP) techniques like topic modeling, linguistic analysis, and sentiment analysis. These are just a few of the ways. We also look into whether network analysis can be used to find fake profiles and automated campaigns to spread false information. We also talk about some of the problems that exist in this field, such as the need for large, annotated datasets and the fact that adversarial attacks are common, both of which are important for figuring out what fake news is. In the end, we suggest some ideas for more research into how machine learning can be used to make it easier and more accurate to spot fake news.

Detection of fake news , Social network , Support vector machine (SVM) , Principal component analysis (PCA)