FAKE DETECTOR EFFECTIVE FAKE NEWS DETECTION WITH DEEP DIFFUSIVE NEURAL NETWORK

Abstract

The rapid growth of social media platforms and online news sources has significantly increased the spread of fake news, posing serious challenges to public trust, social stability, and informed decisionmaking. Fake news often contains misleading, manipulated, or entirely fabricated information that can influence public opinion and create widespread misinformation. Traditional fake news detection methods rely on manual verification and rule-based systems, which are often inefficient in handling large volumes of rapidly generated content. This paper presents Fake Detector: Effective Fake News Detection with Deep Diffusive Neural Network, an intelligent framework designed to identify and classify fake news articles with high accuracy. The proposed approach employs deep diffusive neural networks to capture complex semantic relationships, contextual information, and propagation patterns within textual content. Natural Language Processing (NLP) techniques are utilized for text preprocessing, feature extraction, and representation learning, enabling the model to effectively distinguish between genuine and fake news. Experimental analysis demonstrates that the proposed framework achieves superior detection performance, enhances classification accuracy, and reduces misinformation dissemination. The developed system provides a scalable and reliable solution for combating fake news in modern digital communication environments.