The Role of Individual User Differences in Interpretable and Explainable Machine Learning Systems
This research addresses the problem of designing more effective and user-friendly ML systems for non-expert audiences by considering individual differences, though it is incremental as it builds on existing theories like Fuzzy Trace Theory.
The study investigated how individual user differences, such as skills and personality traits, affect interpretability and explainability in machine learning systems, finding that interpretability and explainability are distinct and that traits like metacognitive monitoring improve interpretability, though familiarity with ML systems did not always lead to meaningful insights.
There is increased interest in assisting non-expert audiences to effectively interact with machine learning (ML) tools and understand the complex output such systems produce. Here, we describe user experiments designed to study how individual skills and personality traits predict interpretability, explainability, and knowledge discovery from ML generated model output. Our work relies on Fuzzy Trace Theory, a leading theory of how humans process numerical stimuli, to examine how different end users will interpret the output they receive while interacting with the ML system. While our sample was small, we found that interpretability -- being able to make sense of system output -- and explainability -- understanding how that output was generated -- were distinct aspects of user experience. Additionally, subjects were more able to interpret model output if they possessed individual traits that promote metacognitive monitoring and editing, associated with more detailed, verbatim, processing of ML output. Finally, subjects who are more familiar with ML systems felt better supported by them and more able to discover new patterns in data; however, this did not necessarily translate to meaningful insights. Our work motivates the design of systems that explicitly take users' mental representations into account during the design process to more effectively support end user requirements.