Fiper: a Visual-based Explanation Combining Rules and Feature Importance
This work addresses the need for user-centered explainable AI in high-stakes domains, though it appears incremental as it builds on existing visual and rule-based approaches.
The paper tackled the problem of making AI predictions more interpretable by proposing a visual-based method that combines rules and feature importance, and a user study with 15 participants showed its effectiveness compared to original algorithm outputs and textual representations.
Artificial Intelligence algorithms have now become pervasive in multiple high-stakes domains. However, their internal logic can be obscure to humans. Explainable Artificial Intelligence aims to design tools and techniques to illustrate the predictions of the so-called black-box algorithms. The Human-Computer Interaction community has long stressed the need for a more user-centered approach to Explainable AI. This approach can benefit from research in user interface, user experience, and visual analytics. This paper proposes a visual-based method to illustrate rules paired with feature importance. A user study with 15 participants was conducted comparing our visual method with the original output of the algorithm and textual representation to test its effectiveness with users.