Data Analysis in the Era of Generative AI
It addresses the problem of making data analysis more accessible and efficient for users through AI integration, but is primarily a conceptual exploration rather than presenting new technical results.
This paper examines how generative AI tools can transform data analysis workflows by translating user intentions into code and visualizations, while identifying key design principles and research challenges for developing effective AI-assisted systems.
This paper explores the potential of AI-powered tools to reshape data analysis, focusing on design considerations and challenges. We explore how the emergence of large language and multimodal models offers new opportunities to enhance various stages of data analysis workflow by translating high-level user intentions into executable code, charts, and insights. We then examine human-centered design principles that facilitate intuitive interactions, build user trust, and streamline the AI-assisted analysis workflow across multiple apps. Finally, we discuss the research challenges that impede the development of these AI-based systems such as enhancing model capabilities, evaluating and benchmarking, and understanding end-user needs.