Jeremy E. Block

Jeremy E. Block, Eric D. Ragan

Many interactive data systems combine visual representations of data with embedded algorithmic support for automation and data exploration. To effectively support transparent and explainable data systems, it is important for researchers and designers to know how users understand the system. We discuss the evaluation of users' mental models of system logic. Mental models are challenging to capture and analyze. While common evaluation methods aim to approximate the user's final mental model after a period of system usage, user understanding continuously evolves as users interact with a system over time. In this paper, we review many common mental model measurement techniques, discuss tradeoffs, and recommend methods for deeper, more meaningful evaluation of mental models when using interactive data analysis and visualization systems. We present guidelines for evaluating mental models over time that reveal the evolution of specific model updates and how they may map to the particular use of interface features and data queries. By asking users to describe what they know and how they know it, researchers can collect structured, time-ordered insight into a user's conceptualization process while also helping guide users to their own discoveries.

Sina Mohseni, Jeremy E. Block, Eric D. Ragan

Research in interpretable machine learning proposes different computational and human subject approaches to evaluate model saliency explanations. These approaches measure different qualities of explanations to achieve diverse goals in designing interpretable machine learning systems. In this paper, we propose a human attention benchmark for image and text domains using multi-layer human attention masks aggregated from multiple human annotators. We then present an evaluation study to evaluate model saliency explanations obtained using Grad-cam and LIME techniques. We demonstrate our benchmark's utility for quantitative evaluation of model explanations by comparing it with human subjective ratings and ground-truth single-layer segmentation masks evaluations. Our study results show that our threshold agnostic evaluation method with the human attention baseline is more effective than single-layer object segmentation masks to ground truth. Our experiments also reveal user biases in the subjective rating of model saliency explanations.