XFake: Explainable Fake News Detector with Visualizations

Abstract

In this demo paper, we present the XFake system, an explainable fake news detector that assists end-users to identify news credibility. To effectively detect and interpret the fakeness of news items, we jointly consider both attributes (e.g., speaker) and statements. Specifically, MIMIC, ATTN and PERT frameworks are designed, where MIMIC is built for attribute analysis, ATTN is for statement semantic analysis and PERT is for statement linguistic analysis. Beyond the explanations extracted from the designed frameworks, relevant supporting examples as well as visualization are further provided to facilitate the interpretation. Our implemented system is demonstrated on a real-world dataset crawled from PolitiFact, where thousands of verified political news have been collected.

4 pages, WebConf'2019 Demo

References in corpus (2)

• XGBoost: A Scalable Tree Boosting System
• Distributed Representations of Words and Phrases and their Compositionality

Cited by in corpus (15)

• A Survey of Fake News: Fundamental Theories, Detection Methods, and Opportunities
• On Explainability of Graph Neural Networks via Subgraph Explorations
• The State of Human-centered NLP Technology for Fact-checking
• A Kernel of Truth: Determining Rumor Veracity on Twitter by Diffusion Pattern Alone
• Adaptive Interaction Fusion Networks for Fake News Detection
• What Does Evaluation of Explainable Artificial Intelligence Actually Tell Us? A Case for Compositional and Contextual Validation of XAI Building Blocks
• Open Issues in Combating Fake News: Interpretability as an Opportunity
• Explainable Rumor Detection using Inter and Intra-feature Attention Networks
• iCapsNets: Towards Interpretable Capsule Networks for Text Classification
• Adversarial Attacks and Defenses: An Interpretation Perspective
• ExClaim: Explainable Neural Claim Verification Using Rationalization
• Disinformation in the Online Information Ecosystem: Detection, Mitigation and Challenges
• Challenges and Considerations with Code-Mixed NLP for Multilingual Societies
• Towards Explainable Fact Checking
• Identification and explanation of disinformation in wiki data streams