A New cross-domain strategy based XAI models for fake news detection

TL;DR

This paper introduces a four-level cross-domain strategy for fake news detection using pre-trained models, integrating explainability techniques to enhance understanding of model behaviour across diverse domains.

Contribution

It proposes a novel four-level cross-domain approach combining fine-tuned BERT with multiple XAI models for improved fake news detection and interpretability.

Findings

Identified effective XAI model pairs for different cross-domain levels

Demonstrated improved fake news detection accuracy across domains

Provided insights into model behaviour with explainability tools

Abstract

In this study, we presented a four-level cross-domain strategy for fake news detection on pre-trained models. Cross-domain text classification is a task of a model adopting a target domain by using the knowledge of the source domain. Explainability is crucial in understanding the behaviour of these complex models. A fine-tune BERT model is used to. perform cross-domain classification with several experiments using datasets from different domains. Explanatory models like Anchor, ELI5, LIME and SHAP are used to design a novel explainable approach to cross-domain levels. The experimental analysis has given an ideal pair of XAI models on different levels of cross-domain.