Strategies for Enhancing Fabricated News Detection: A Machine Learning Approach

Abstract

Fake news, or fabricated news, poses a significant threat to trust in government and democracy by disseminating false information to influence political views. The issue under consideration receives considerable attention from researchers because of its increasing popularity. This review paper examines the existing advancements concerning countering fake news and introduces ensemble methodologies for the news articles binary classification. The research demonstrates the efficiency of machine learning algorithms, such as Passive Aggressive, Naïve Bayes, and Support Vector Machine classifiers, in the detection of fabricated news content. Nevertheless, it also underscores the constraints of basic classification techniques and underscores the necessity for specialized methodologies specifically designed for identifying fake news. This paper highlights the issue of limited data availability in this field and urges the need for effective techniques to differentiate between fake and authentic news sources.