Trust Oriented Explainable AI for Fake News Detection

TL;DR

This paper explores how explainable AI techniques like SHAP, LIME, and Integrated Gradients improve transparency and trust in NLP-based fake news detection models, balancing interpretability with accuracy.

Contribution

It compares multiple XAI methods in fake news detection, highlighting their strengths, limitations, and impact on model transparency and trustworthiness.

Findings

XAI enhances model interpretability without sacrificing accuracy

Different XAI methods offer unique explanatory insights

Computational cost and parameter sensitivity are notable limitations

Abstract

This article examines the application of Explainable Artificial Intelligence (XAI) in NLP based fake news detection and compares selected interpretability methods. The work outlines key aspects of disinformation, neural network architectures, and XAI techniques, with a focus on SHAP, LIME, and Integrated Gradients. In the experimental study, classification models were implemented and interpreted using these methods. The results show that XAI enhances model transparency and interpretability while maintaining high detection accuracy. Each method provides distinct explanatory value: SHAP offers detailed local attributions, LIME provides simple and intuitive explanations, and Integrated Gradients performs efficiently with convolutional models. The study also highlights limitations such as computational cost and sensitivity to parameterization. Overall, the findings demonstrate that integrating XAI with NLP is an effective approach to improving the reliability and trustworthiness of fake news detection systems.