Exploring Bias in Data and Models for Misinformation Detection from Text

Keyphrases

• Misinformation Detection 100%
• Bias in Data 100%
• News Sources 66%
• Detection Method 33%
• Potential Bias 33%
• Feature Combination 33%
• Content-based 33%
• Misinformation 33%
• Contextualized Word Embeddings 33%
• Label-only 33%
• Reliability Score 33%
• Post-hoc Explanation 33%
• Network Features 33%
• Bag-of-words Model 33%
• Metadata Features 33%
• Large Language Models 33%
• Fact-checking Organizations 33%
• Error Analysis 33%
• Model Driven Architecture 33%
• News Websites 33%
• Automatic Creation 33%
• Text Features 33%
• Detection Dataset 33%
• Training Data 33%

Computer Science

• Misinformation 100%
• Baseline Model 25%
• Model Architecture 25%
• Detection Method 25%
• Training Data 25%
• Large Language Model 25%
• SHapley Additive exPlanation 25%
• Word Embedding 25%