A System to Track Fabricated Content in Social media using Machine Learning Approach

In today’s society, when the internet is pervasive, everyone gets their news from a variety of online sources. Information can swiftly reach millions of users in a short amount of time due to the growing usage of social media sites like Facebook, Twitter, and others. Fake news has far-reaching effects, ranging from swaying election outcomes in favor of particular politicians to fostering prejudiced viewpoints. The primary platforms for disseminating fake news are Instagram, WhatsApp, and numerous other social media platforms. By presenting a machine learning-based fake news detection algorithm, this work provides a remedy. This model needs fictitious data that was gathered from multiple information sources. Data is extracted using web analytics, which is mostly used to build datasets. Real data sets and fake data sets are the two primary categories into which the data is separated. Random forest, logistic regression, decision trees, KNN, and gradient boosting are the classifiers used to classify the data. The data is categorized as true or false data based on the version that was received. The user will be able to determine whether or not the information on the website is fraudulent based on this.