A Test Collection for Dataset Retrieval in Biodiversity Research

@article{10.3897/rio.7.e67887,
	author = {Felicitas Löffler and Andreas Schuldt and Birgitta König-Ries and Helge Bruelheide and Friederike Klan},
	title = {A Test Collection for Dataset Retrieval in Biodiversity Research},
	volume = {7},
	number = {},
	year = {2021},
	doi = {10.3897/rio.7.e67887},
	publisher = {Pensoft Publishers},
	abstract = {Searching for scientific datasets is a prominent task in scholars' daily research practice. A variety of data publishers, archives and data portals offer search applications that allow the discovery of datasets. The evaluation of such dataset retrieval systems requires proper test collections, including questions that reflect real world information needs of scholars, a set of datasets and human judgements assessing the relevance of the datasets to the questions in the benchmark corpus. Unfortunately, only very few test collections exist for a dataset search. In this paper, we introduce the BEF-China test collection, the very first test collection for dataset retrieval in biodiversity research, a research field with an increasing demand in data discovery services. The test collection consists of 14 questions, a corpus of 372 datasets from the BEF-China project and binary relevance judgements provided by a biodiversity expert.},
	issn = {},
	pages = {e67887},
	URL = {https://doi.org/10.3897/rio.7.e67887},
	eprint = {https://doi.org/10.3897/rio.7.e67887},
	journal = {Research Ideas and Outcomes}
}