The Feature Understandability Scale for Human-Centred Explainable AI: Assessing Tabular Feature Importance

As artificial intelligence becomes increasingly pervasive and powerful, the ability to audit AI-based systems is growing in importance. However, explainability for artificial intelligence systems is not a one-size-fits-all solution; different target audiences have varying requirements and expectations for explanations. While various approaches to explainability have been proposed, most explainable artificial intelligence methods for tabular data focus on explaining the outputs of supervised machine learning mod-els using the input features. However, a user’s ability to understand an explanation depends on their understanding of such features. Therefore, it is in the best interest of the system designer to try to pre-select under-standable features for producing a global explanation of an ML model. Unfortunately, no measure currently exists to assess the degree to which a user understands a given input feature. This work introduces two psy-chometrically validated scales that quantitatively seek to assess users’ per-ceived understanding of tabular input features for supervised classification problems. Specifically, these scales, one for numerical and one for categori-cal data, each with two factors and comprising 8 and 9 items, aim to assign a score to each input feature, effectively producing a rank and allowing for the quantification of feature prioritisation. A confirmatory factor analysis demonstrates a strong relationship between such items and a good fit of the two-factor structure for each scale. This research presents a novel method for assessing understanding and outlines potential applications in the domain of explainable artificial intelligence.