Improving data discovery effectiveness: experimental evaluation of content-based catalogs in data spaces

Abstract

Data spaces facilitate sovereignty-preserving data sharing within federated ecosystems; however, dataset discovery is often constrained by catalogs that rely primarily on high-level metadata standards such as DCAT-AP. These models typically lack structural and content-level details, which impedes fine-grained relevance assessment and complicates both internal dataset discovery and the federation of external open data into data spaces. This paper introduces cbmDCAT-AP, a backward-compatible extension of DCAT-AP that integrates content-based metadata as primary catalog elements. The proposed extension augments dataset descriptions with field-level semantics, and representative sample values, thereby enabling content-informed discovery without disclosing entire datasets. Furthermore, a clustering-based reduction technique is proposed to generate representative samples values through the use of word embeddings and K-means clustering. Finally, an end-to-end evaluation across two scenarios (internal dataset discovery and external open data selection) has been conducted to evaluate and validate our proposed extension of DCAT-AP.