Metraipolis › archive › dc_855f7aae64ec
Exploratory Unstructured Data Analysis: A Formative Study and Implications for Human-AI Collaboration — arXiv:2609.03678
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.03678
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T02:04:24.299Z
- SHA-256 of the archived text
ba2bb98fd4872d9799813fb3ba948a80a77ae06f5d8ddddc370a6cb8917c057c- Stable URL of this page
https://metraipolis.com/documento/dc_855f7aae64ec
How to cite
Exploratory Unstructured Data Analysis: A Formative Study and Implications for Human-AI Collaboration — arXiv:2609.03678 — arXiv (en), https://arxiv.org/abs/2609.03678 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_855f7aae64ec (Metraipolis archive dc_855f7aae64ec, sha256 ba2bb98fd4872d9799813fb3ba948a80a77ae06f5d8ddddc370a6cb8917c057c)
BibTeX
@misc{dc855f7aae64ec,
title = {Exploratory Unstructured Data Analysis: A Formative Study and Implications for Human-AI Collaboration — arXiv:2609.03678},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.03678},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_855f7aae64ec; sha256 ba2bb98fd4872d9799813fb3ba948a80a77ae06f5d8ddddc370a6cb8917c057c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03678. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.HC). Categorie arXiv: Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2609.03678 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T01:37:09.642Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).