Detection of False Statement from Social Media using Machine Learning Algorithms

Abstract

The proliferation of misleading information in everyday access media outlets such as social media feeds, news blogs, and newspapers has made it challenging to identify trustworthy news sources, thus increasing the need for computational tools able to provide insights into the reliability of online content. People intentionally spread these counterfeit statements with the help of web-based social networking sites. The fundamental objective of false statements is to influence the popular belief on specific issues. The main goal of false statements is to affect public opinion on certain matters. The aim of this paper is to find and detect false statements made by individual public figures using machine learning algorithms. A system is proposed in this paper that identifies whether a given statement is false or not by making use of a provided training dataset and the algorithms used. The results are concluding that Logistic Regression provides 98% the highest percentage of accuracy among various machine learning algorithms.