探索性非结构化数据分析：一项形成性研究及对人机协作的启示
Exploratory Unstructured Data Analysis: A Formative Study and Implications for Human-AI Collaboration
- TU Wien（维也纳工业大学）
- University of Applied Sciences St. Pölten (USTP)（圣珀尔滕应用科学大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究提出EluDA框架，通过形成性研究发现用户自下而上构建分面分类、CLIP分配不可靠但支持语义分组，进而明确人机协作的四大关键机遇。
AI中文摘要：
我们提出了针对（大型）非结构化数据探索性数据分析的概念框架EluDA，将经典元素（查询、可视化）与“结构探寻”中的主动知识构建相结合。在一项形成性研究中，用户在探索图像数据集时对其结构进行了概念化。我们发现用户通过自下而上构建分面分类来进行概念化，在此过程中很少创建有意义的空间分类。我们还评估了CLIP在零样本分配和语义分类方面的表现，发现它在将用户定义的概念分配给图像方面仍不可靠，但确实支持语义分组。基于这些发现，我们确定并讨论了EluDA中人机协作的四个关键机遇：智能采样与可视化以最大化数据可见性；增量式少样本学习以最小化可靠分配的工作量；自动类别、概念和分面建议以减少结构探寻过程中的工作量；以及有效信任校准方法的必要性。
英文摘要：
We propose a conceptual framework for exploratory data analysis of (large) unstructured data (EluDA), combining classical elements (querying, visualization) with active knowledge construction in the "search for structure". In a formative study, users conceptualized a structure for an image dataset during exploration. We found that users conceptualize by building faceted classifications bottom-up and rarely create meaningful spatial categorization during this process. We also evaluated CLIP for zero-shot assignment and semantic categorization, finding that it remains unreliable for assigning user-defined concepts to images but does support semantic grouping. Based on these findings, we identify and discuss four key opportunities for human-AI collaboration in EluDA: intelligent sampling and visualization to maximize data visibility; incremental and few-shot learning to minimize effort for reliable assignment; automatic category, concept, and facet suggestions to reduce effort during the search for structure; and the necessity for effective trust calibration methods.
