What Matters in Explanations: Towards Explainable Fake Review Detection Focusing on Transformers

TL;DR

This paper develops a high-accuracy, explainable fake review detection framework using transformer models and layer-wise relevance propagation, providing insights into what information influences detection decisions.

Contribution

It introduces an explainable fake review detection approach with transformer models and empirical evaluation of explanation relevance, advancing interpretability in fraud detection.

Findings

Transformer models achieve state-of-the-art accuracy.

Layer-wise relevance propagation effectively explains model decisions.

User evaluation identifies key information for explanations.

Abstract

Customers' reviews and feedback play crucial role on electronic commerce~(E-commerce) platforms like Amazon, Zalando, and eBay in influencing other customers' purchasing decisions. However, there is a prevailing concern that sellers often post fake or spam reviews to deceive potential customers and manipulate their opinions about a product. Over the past decade, there has been considerable interest in using machine learning (ML) and deep learning (DL) models to identify such fraudulent reviews. Unfortunately, the decisions made by complex ML and DL models - which often function as \emph{black-boxes} - can be surprising and difficult for general users to comprehend. In this paper, we propose an explainable framework for detecting fake reviews with high precision in identifying fraudulent content with explanations and investigate what information matters most for explaining particular decisions by conducting empirical user evaluation. Initially, we develop fake review detection models using DL and transformer models including XLNet and DistilBERT. We then introduce layer-wise relevance propagation (LRP) technique for generating explanations that can map the contributions of words toward the predicted class. The experimental results on two benchmark fake review detection datasets demonstrate that our predictive models achieve state-of-the-art performance and outperform several existing methods. Furthermore, the empirical user evaluation of the generated explanations concludes which important information needs to be considered in generating explanations in the context of fake review identification.