How Do Data Analysts Respond to AI Assistance? A Wizard-of-Oz Study
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916145547706368 |
|---|---|
| author | Gu, Ken Grunde-McLaughlin, Madeleine McNutt, Andrew M. Heer, Jeffrey Althoff, Tim |
| author_facet | Gu, Ken Grunde-McLaughlin, Madeleine McNutt, Andrew M. Heer, Jeffrey Althoff, Tim |
| contents | 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 significant attention, limited research addresses assistance for both analysis execution and planning. In this work, we characterize helpful planning suggestions and their impacts on analysts' workflows. We first 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 findings highlight subtleties in contextual factors that impact suggestion helpfulness, emphasizing design implications for supporting different abstractions of assistance, forms of initiative, increased engagement, and alignment of goals between analysts and assistants. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_10108 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | How Do Data Analysts Respond to AI Assistance? A Wizard-of-Oz Study Gu, Ken Grunde-McLaughlin, Madeleine McNutt, Andrew M. Heer, Jeffrey Althoff, Tim Human-Computer Interaction 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 significant attention, limited research addresses assistance for both analysis execution and planning. In this work, we characterize helpful planning suggestions and their impacts on analysts' workflows. We first 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 findings highlight subtleties in contextual factors that impact suggestion helpfulness, emphasizing design implications for supporting different abstractions of assistance, forms of initiative, increased engagement, and alignment of goals between analysts and assistants. |
| title | How Do Data Analysts Respond to AI Assistance? A Wizard-of-Oz Study |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2309.10108 |