Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs
arXiv:2101.09824 · doi:10.1145/3411764.3445088
Abstract
To ensure accountability and mitigate harm, it is critical that diverse stakeholders can interrogate black-box automated systems and find information that is understandable, relevant, and useful to them. In this paper, we eschew prior expertise- and role-based categorizations of interpretability stakeholders in favor of a more granular framework that decouples stakeholders' knowledge from their interpretability needs. We characterize stakeholders by their formal, instrumental, and personal knowledge and how it manifests in the contexts of machine learning, the data domain, and the general milieu. We additionally distill a hierarchical typology of stakeholder needs that distinguishes higher-level domain goals from lower-level interpretability tasks. In assessing the descriptive, evaluative, and generative powers of our framework, we find our more nuanced treatment of stakeholders reveals gaps and opportunities in the interpretability literature, adds precision to the design and comparison of user studies, and facilitates a more reflexive approach to conducting this research.
In CHI Conference on Human Factors in Computing Systems (CHI '21)
References in corpus (6)
- Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making
- A systematic review and taxonomy of explanations in decision support and recommender systems
- Explaining Models: An Empirical Study of How Explanations Impact Fairness Judgment
- Human Factors in Model Interpretability: Industry Practices, Challenges, and Needs
- Misplaced Trust: Measuring the Interference of Machine Learning in Human Decision-Making
- An Exploratory Study on Visual Exploration of Model Simulations by Multiple Types of Experts