Article
FAKE NEWS DETECTION SYSTEM USING FEATURE-BASED OPTIMIZED MSVM CLASSIFICATION
The exponential growth of online content and social media platforms has accelerated the spread of fake news, posing serious threats to societal stability, democratic processes, and public trust. Automatic fake news detection has thus emerged as a crucial research problem in the domains of Natural Language Processing (NLP) and Machine Learning (ML). This paper proposes a Feature-Based Optimized Multiclass Support Vector Machine (MSVM) classification framework to effectively detect and classify fake news. The proposed system leverages advanced text preprocessing techniques, hybrid feature extraction methods (including TF-IDF, n-grams, sentiment analysis, and linguistic cues), and feature optimization techniques such as Chi-square and Principal Component Analysis (PCA). The optimized MSVM classifier is designed to handle high-dimensional feature spaces and multi-class classification efficiently. Experimental evaluation demonstrates that the proposed system significantly improves classification accuracy, robustness, and scalability compared to traditional methods. The system is suitable for real-time deployment in social media monitoring and news verification platforms.
Full Text Attachment
