MACHINE LEARNING FOR TRUTH DISCOVERY:A REVIEW OF FAKE NEWS, PROPAGANDA AUTHOR, AND THEIR INFLUENCE ON SOCIETY

Abstract

The widespread use of social media and digital communication platforms has significantly increased the dissemination of fake news, propaganda, and misleading information, creating substantial challenges for society, governments, and information consumers. The rapid spread of false information can influence public opinion, affect political and social decisions, and undermine trust in credible information sources. Machine learning has emerged as a powerful tool for truth discovery by automatically analyzing large volumes of textual and multimedia content to identify deceptive information patterns. This paper presents a comprehensive review of machine learning approaches for truth discovery, focusing on fake news detection, propaganda author identification, and the societal impact of misinformation. Various machine learning, deep learning, and Natural Language Processing techniques are examined for their effectiveness in content classification, source verification, sentiment analysis, and author profiling. The review highlights recent advancements, challenges, and opportunities in automated truth discovery systems. Furthermore, the study explores how misinformation and propaganda influence public perception, social behavior, and decision-making processes. The findings demonstrate that machine learning-based truth discovery systems play a critical role in combating misinformation and promoting information credibility in the digital age.