Abstract

In recent years, the proliferation of online social networks has led to a surge in fake news, which is deliberately spread for various commercial and political motives. This phenomenon has significantly impacted offline society, as deceptive information can easily infect users of these platforms. Addressing this issue is crucial for enhancing the credibility of information shared online.This study focuses on investigating methods, principles, and algorithms aimed at detecting fake news articles, their creators, and related topics within online social networks. The goal is to promptly identify and mitigate the spread of misleading information. The challenge lies in the vast scale of online data, particularly on social media platforms, which complicates the task of distinguishing and correcting inaccuracies, commonly referred to as "fake news."The proposed approach in this research involves using a Naive Bayes classification model to predict whether posts on Facebook are genuine or fabricated. The effectiveness of this method is further enhanced through various techniques discussed in the paper. The findings indicate that machine learning techniques can effectively address the problem of fake news detection, offering potential solutions to mitigate its harmful effects in online environments.