Enhancing Social Media Integrity: A Machine Learning-Based Rumor Identification System Utilizing CNN for Accurate Real-Time Tweet Analysis

This research introduces a machine learning framework for real-time rumor detection on social media platforms, particularly focusing on tweet classification. Several machine learning approaches, including Support Vector Machine (SVM), Logistic Regression, Naïve Bayes, Random Forest, and a Convolutional Neural Network (CNN), are explored. An ensemble model integrating Random Forest, SVM, and Logistic Regression is also examined. The CNN architecture demonstrates the highest accuracy (88%), outperforming the ensemble model (87%) and SVM (87%). CNN's superior performance is attributed to its ability to capture deep linguistic patterns and contextual nuances in social media content. The system features an intuitive user interface for immediate analysis, offering a practical solution to combat misinformation. The results underscore the potential of advanced machine learning techniques in enhancing the accuracy and efficiency of automated rumor detection.