Knowledge-organization strategy during exploratory data analysis

Determine whether analysts construct an explicit knowledge structure before classifying observed data, derive tags or faceted concepts from observations in a bottom-up manner, or categorize data into equivalent groups without initially using natural-language descriptions during exploratory analysis of unstructured data.

Background

The paper distinguishes several possible ways in which analysts may organize knowledge while exploring unstructured data. A top-down strategy would involve constructing an explicit structure first and then classifying observations; a bottom-up strategy would derive tags or faceted concepts from the data; and a categorization strategy would group equivalent data items without necessarily assigning textual descriptions. The authors state that it remains unresolved which of these strategies analysts actually prefer, and note that the answer has implications for the design of knowledge-externalization interfaces.

References

It is unclear whether analysts aim to first construct an explicit knowledge structure to later classify the observed data top-down, whether they rather observe the data first and then derive a set of tags or faceted concepts therefrom in a bottom-up manner, or whether they prefer to categorize the data into equivalent groups without a natural-language description thereof, while potentially deriving a taxonomy or set of tags from these categories.

— Exploratory Unstructured Data Analysis: A Formative Study and Implications for Human-AI Collaboration  (2609.03678 - Eschner et al., 3 Sep 2026) in Section 2.1, “Knowledge Organization”