Experiments on Detecting Fake News using Machine Learning Algorithms

Abstract

Spreading fake news has become a serious issue in the current social media world. It is broadcasted with dishonest intentions to mislead people. This has caused many unfortunate incidents in different countries. The most recent one was the latest presidential elections where the voters were misleading to support a leader. Twitter is a popular social media platform where it represents the gateway for real time news. We extracted real time data on multiple domains through twitter and performed analysis. The dataset was preprocessed and user verified column played a vital role. Multiple machine algorithms were then performed on the extracted features from preprocessed dataset. Logistic Regression and Support Vector Machine had promising results with both above 92% accuracy. Naive Bayes and Long-Short Term memory didn’t achieve desired accuracies. The model can also be applied to images and videos for better detection of fake news.