@conference{724,
  keywords = {exploratory data analysis, Visual analytics, mixed-methods evaluation},
  author = {Johannes Eschner and Dominik Eitler and Max Irendorfer and Patrick Kramml and Matthias Zeppelzauer and Waldner, Manuela},
  title = {Exploratory Unstructured Data Analysis: A Formative Study and Implications for Human-AI Collaboration},
  abstract = {<p>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.</p>},
  year = {2026},
  journal = {14th Nordic Conference on Human-Computer Interaction (NordiCHI 2026)},
  pages = {16},
  month = {10/2026},
  publisher = {Association for Computing Machinery},
  address = {Vaasa},
  isbn = {979-8-4007-2373-5},
  doi = {10.1145/3829807.3829882},
}