Interpretability is not Explainability: New Quantitative XAI Approach with a focus on Recommender Systems in Education
This addresses the problem of inconsistent terminology and evaluation in XAI for researchers and practitioners, though it is incremental as it builds on existing frameworks.
The paper tackles the lack of a widely accepted taxonomy for quantitative evaluation of explainability in XAI by proposing a novel taxonomy based on dimensions like transparency and interpretability, and demonstrates its utility through a case study on a recommender system in education using SHAP to quantify explainability.
The field of eXplainable Artificial Intelligence faces challenges due to the absence of a widely accepted taxonomy that facilitates the quantitative evaluation of explainability in Machine Learning algorithms. In this paper, we propose a novel taxonomy that addresses the current gap in the literature by providing a clear and unambiguous understanding of the key concepts and relationships in XAI. Our approach is rooted in a systematic analysis of existing definitions and frameworks, with a focus on transparency, interpretability, completeness, complexity and understandability as essential dimensions of explainability. This comprehensive taxonomy aims to establish a shared vocabulary for future research. To demonstrate the utility of our proposed taxonomy, we examine a case study of a Recommender System designed to curate and recommend the most suitable online resources from MERLOT. By employing the SHAP package, we quantify and enhance the explainability of the RS within the context of our newly developed taxonomy.