On the Evaluation of the Plausibility and Faithfulness of Sentiment Analysis Explanations

TL;DR

This paper proposes a unified evaluation framework for sentiment analysis explanations, assessing faithfulness and plausibility through new metrics, and compares different models and explanation methods, highlighting the superior explainability of transformer architectures.

Contribution

It introduces novel metrics inspired by information retrieval to evaluate sentiment analysis explanations, and provides empirical insights into the performance of various architectures and explanation methods.

Findings

Anchors explanations align better with human judgment.

Reasoning complexity reduces explanation quality.

Transformers outperform other architectures in explainability.

Abstract

Current Explainable AI (ExAI) methods, especially in the NLP field, are conducted on various datasets by employing different metrics to evaluate several aspects. The lack of a common evaluation framework is hindering the progress tracking of such methods and their wider adoption. In this work, inspired by offline information retrieval, we propose different metrics and techniques to evaluate the explainability of SA models from two angles. First, we evaluate the strength of the extracted "rationales" in faithfully explaining the predicted outcome. Second, we measure the agreement between ExAI methods and human judgment on a homegrown dataset1 to reflect on the rationales plausibility. Our conducted experiments comprise four dimensions: (1) the underlying architectures of SA models, (2) the approach followed by the ExAI method, (3) the reasoning difficulty, and (4) the homogeneity of the ground-truth rationales. We empirically demonstrate that anchors explanations are more aligned with the human judgment and can be more confident in extracting supporting rationales. As can be foreseen, the reasoning complexity of sentiment is shown to thwart ExAI methods from extracting supporting evidence. Moreover, a remarkable discrepancy is discerned between the results of different explainability methods on the various architectures suggesting the need for consolidation to observe enhanced performance. Predominantly, transformers are shown to exhibit better explainability than convolutional and recurrent architectures. Our work paves the way towards designing more interpretable NLP models and enabling a common evaluation ground for their relative strengths and robustness.