Improving Explanations: Applying the Feature Understandability Scale for Cost-Sensitive Feature Selection
This work addresses the need for more interpretable AI explanations for users, but it is incremental as it builds on existing methods without introducing a new paradigm.
The study tackled the problem of making AI explanations more understandable by quantifying feature-level understanding using the Feature Understandability Scale, and found that accuracy and understandability can be co-optimized while maintaining high classification performance, with explanations considered more understandable at face value.
With the growing pervasiveness of artificial intelligence, the ability to explain the inferences made by machine learning models has become increasingly important. Numerous techniques for model explainability have been proposed, with natural-language textual explanations among the most widely used approaches. When applied to tabular data, these explanations typically draw on input features to justify a given inference. Consequently, a user's ability to interpret the explanation depends on their understanding of the input features. To quantify this feature-level understanding, Rossberg et al. introduced the Feature Understandability Scale. Building on that work, this proof-of-concept study collects understandability scores across two datasets, proposes a co-optimisation methodology of understandability and accuracy and presents the resulting explanations alongside the model accuracies. This work contributes to the body of knowledge on model interpretability by design. It is found that accuracy and understandability can be successfully co-optimised while maintaining high classification performances. The resulting explanations are considered more understandable at face value. Further research will aim to confirm these findings through user evaluation.