Survey for Categorising Explainable AI Studies Using Data Analysis Task Frameworks
This work addresses the challenge for XAI researchers and designers in navigating a rapidly growing field with inconsistent findings, though it is incremental as it builds on existing frameworks from visual analytics and cognition.
The paper tackles the problem of contradictions and lack of concrete design recommendations in explainable AI (XAI) research for data analysis tasks by proposing a method to categorize and compare XAI studies based on what, why, and who dimensions, aiming to improve the community's ability to parse the field and identify relevant studies.
Research into explainable artificial intelligence (XAI) for data analysis tasks suffer from a large number of contradictions and lack of concrete design recommendations stemming from gaps in understanding the tasks that require AI assistance. In this paper, we drew on multiple fields such as visual analytics, cognition, and dashboard design to propose a method for categorising and comparing XAI studies under three dimensions: what, why, and who. We identified the main problems as: inadequate descriptions of tasks, context-free studies, and insufficient testing with target users. We propose that studies should specifically report on their users' domain, AI, and data analysis expertise to illustrate the generalisability of their findings. We also propose study guidelines for designing and reporting XAI tasks to improve the XAI community's ability to parse the rapidly growing field. We hope that our contribution can help researchers and designers better identify which studies are most relevant to their work, what gaps exist in the research, and how to handle contradictory results regarding XAI design.