How Do Data Analysts Respond to AI Assistance? A Wizard-of-Oz Study

Abstract

Data analysis is challenging as analysts must navigate nuanced decisions that may yield divergent conclusions. AI assistants have the potential to support analysts in planning their analyses, enabling more robust decision making. Though AI-based assistants that target code execution (e.g., Github Copilot) have received signifcant attention, limited research addresses assistance for both analysis execution and planning. In this work, we characterize helpful planning suggestions and their impacts on analysts' workfows. We frst review the analysis planning literature and crowd-sourced analysis studies to categorize suggestion content. We then conduct a Wizard-of-Oz study (n=13) to observe analysts' preferences and reactions to planning assistance in a realistic scenario. Our fndings highlight subtleties in contextual factors that impact suggestion helpfulness, emphasizing design implications for supporting diferent abstractions of assistance, forms of initiative, increased engagement, and alignment of goals between analysts and assistants.