A Framework for Considering Comprehensibility in Modeling

By Michael Gleicher. 2016

62 citations recorded by the source corpus.

Abstract Comprehensibility in modeling is the ability of stakeholders to understand relevant aspects of the modeling process. In this article, we provide a framework to help guide exploration of the space of comprehensibility challenges. We consider facets organized around key questions: Who is comprehending? Why are they trying to comprehend? Where in the process are they trying to comprehend? How can we help them comprehend? How do we measure their comprehension? With each facet we consider the broad range of options. We discuss why taking a broad view of comprehensibility in modeling is useful in identifying challenges and opportunities for solutions.

Subfields: Computer Vision and Pattern Recognition, Information Systems, Management Information Systems, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Information Systems

In Management Information Systems

In Safety, Robustness & Interpretability

Citations in the corpus

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, neutral): “• Comprehensibility: when conceived for ML models, comprehensibility refers to the ability of a learning algorithm to represent its learned knowledge in a human understandable fashion [19, 20, 21].”
Simple Rules for Complex Decisions (2017, background): “e clarity of simple rules engenders trust from users, providing insight into how systems work and exposing where models may be improved [11, 32].”
Simple rules to guide expert classifications (2020, background): “The clarity of simple rules provides insight into how systems work and exposes where models may be improved (Gleicher, 2016; Sull and Eisenhardt, 2015), which may encourage adoption of such tools in clinical settings (Wyatt and Altman, 1995).”
Benchmarking and survey of explanation methods for black box models (2021, background): “2019c), or comprehensibility (Gleicher 2016), is the ability of stakeholders to understand relevant aspects of the modeling pro-”
Evolutionary Fuzzy Systems for Explainable Artificial Intelligence: Why, When, What for, and Where to? (2019, background): “Zadeh emphasized that this semantic cointension was the key for understanding the success of the application of fuzzy models, namely the importance of the human component in the data science process [15].”
A comprehensive taxonomy for explainable artificial intelligence: a systematic survey of surveys on methods and concepts (2021, background): “Stakeholder perspective Gleicher 2016 [53], Langer et al.”