XAI-enhanced Comparative Opinion Mining via Aspect-based Scoring and Semantic Reasoning

TL;DR

This paper introduces XCom, an interpretable transformer-based model for comparative opinion mining that combines aspect-based scoring and semantic reasoning, enhancing transparency and trustworthiness in product review analysis.

Contribution

The paper presents XCom, a novel model integrating explanation modules into transformer-based opinion mining for improved interpretability and performance.

Findings

XCom outperforms baseline models in accuracy.

XCom provides meaningful explanations of its decisions.

The model enhances trust in opinion mining results.

Abstract

Comparative opinion mining involves comparing products from different reviews. However, transformer-based models designed for this task often lack transparency, which can adversely hinder the development of trust in users. In this paper, we propose XCom, an enhanced transformer-based model separated into two principal modules, i.e., (i) aspect-based rating prediction and (ii) semantic analysis for comparative opinion mining. XCom also incorporates a Shapley additive explanations module to provide interpretable insights into the model's deliberative decisions. Empirically, XCom achieves leading performances compared to other baselines, which demonstrates its effectiveness in providing meaningful explanations, making it a more reliable tool for comparative opinion mining. Source code is available at: https://anonymous.4open.science/r/XCom.