Contextualization and Exploration of Local Feature Importance Explanations to Improve Understanding and Satisfaction of Non-Expert Users

Clara Bove (1, 2) , Jonathan Aigrain , Marie-Jeanne Lesot (2) , Charles Tijus , Marcin Detyniecki

1 AXA - Groupe AXA
2 LFI - Learning, Fuzzy and Intelligent systems

The increasing usage of complex Machine Learning models for decision-making has raised interest in explainable artificial intelligence (XAI). In this work, we focus on the effects of providing accessible and useful explanations to non-expert users. More specifically, we propose generic XAI design principles for contextualizing and allowing the exploration of explanations based on local feature importance. To evaluate the effectiveness of these principles for improving users' objective understanding and satisfaction, we conduct a controlled user study with 80 participants using 4 different versions of our XAI system, in the context of an insurance scenario. Our results show that the contextualization principles we propose significantly improve user's satisfaction and is close to have a significant impact on user's objective understanding. They also show that the exploration principles we propose improve user's satisfaction. On the other hand, the interaction of these principles does not appear to bring improvement on both dimensions of users' understanding. CCS CONCEPTS • Human-centered computing → User studies; HCI theory, concepts and models.

Mots clés: explainable AI; human-centered AI methods; user studies; interface design

Domaines: Interface homme-machine [cs.HC]; Intelligence artificielle [cs.AI]; Informatique

Clara Bove, Jonathan Aigrain, Marie-Jeanne Lesot, Charles Tijus, Marcin Detyniecki. Contextualization and Exploration of Local Feature Importance Explanations to Improve Understanding and Satisfaction of Non-Expert Users. IUI '22: 27th International Conference on Intelligent User Interfaces, Mar 2022, Helsinki, Finland. pp.807-819, ⟨10.1145/3490099.3511139⟩. ⟨hal-03601793⟩