How to explain it to data scientists? A mixed-methods user study about explainable AI, using mental models for explanations

TL;DR

This study explores data scientists' explanation needs in XAI, developing a mental model to improve explanations by organizing complex content causally and hierarchically, validated through qualitative and quantitative research.

Contribution

It introduces a mental model for explanations tailored to data scientists, emphasizing content organization and the use of standardized questions to enhance explanation quality.

Findings

Explanation content derives from application, system, and AI domains.

Content should be organized sequentially and hierarchically.

Explanation includes context, evidence, relationships, and causal stories.

Abstract

In the context of explainable artificial intelligence (XAI), limited research has identified role-specific explanation needs. This study investigates the explanation needs of data scientists, who are responsible for training, testing, deploying, and maintaining machine learning (ML) models in AI systems. The research aims to determine specific explanation content of data scientists. A task analysis identified user goals and proactive user tasks. Using explanation questions, task-specific explanation needs and content were identified. From these individual explanations, we developed a mental model for explanations, which was validated and revised through a qualitative study (n=12). In a second quantitative study (n=12), we examined which explanation intents (reason, comparison, accuracy, prediction, trust) require which type of explanation content from the mental model. The findings are: F1: Explanation content for data scientists comes from the application domain, system domain, and AI domain. F2: Explanation content can be complex and should be organized sequentially and/or in hierarchies (novelty claim). F3: Explanation content includes context, inputs, evidence, attributes, ranked list, interim results, efficacy principle, and input/output relationships (novelty claim). F4: Explanation content should be organized as a causal story. F5: Standardized explanation questions ensure complete coverage of explanation needs (novelty claim). F6: Refining mental models for explanations increases significantly its quality (novelty claim).