Ensemble Learning for Fake News Detection: Enhancing Classification Accuracy and Explainability with Structural and Statistical Metadata

Keyphrases

• Accurate Classification 33%
• Article Length 33%
• Classification Accuracy 100%
• Classification Decision 33%
• Classification Model 33%
• Detection System 33%
• Digital Platforms 33%
• Enhanced Model 33%
• Ensemble Learning 100%
• Ensemble Learning Model 33%
• Explainability 100%
• Explainable Classification 33%
• F1 Score 33%
• Fact-checking 33%
• Fact-checking Journalism 33%
• Fake News 33%
• Fake News Classification 33%
• Fake News Dataset 33%
• Fake News Detection 100%
• Highly Accurate 33%
• Hybrid Machine Learning 33%
• Individual Classifiers 33%
• Influential Features 33%
• Logistic Regression 33%
• Metadata Features 33%
• Misinformation 33%
• Misinformation Detection 66%
• Model Transparency 33%
• Natural Language Processing 33%
• Real-world Application 33%
• ROC-AUC 33%
• Shapley Additive Explanations 33%
• Social Media Moderation 33%
• Societal Challenges 33%
• Stacking Ensemble Learning 33%
• Stacking Ensemble Model 33%
• Statistical Metadata 100%
• Structural Information 100%
• Textual Analysis 33%
• Textual Information 33%
• Viable Solutions 33%
• XGBoost Regression 33%

Computer Science

• Classification Accuracy 100%
• Classification Models 33%
• Digital Platform 33%
• Ensemble Learning 100%
• Experimental Result 33%
• Extreme Gradient Boosting 33%
• Fake News Detection 100%
• Generalizability 33%
• Individual Classifier 33%
• Interpretability 33%
• Logistic Regression 33%
• Machine Learning Approach 33%
• Metadata 100%
• Misinformation 100%
• Natural Language Processing 33%
• Processing Approach 33%
• SHapley Additive exPlanation 33%
• Social Media 33%
• World Application 33%