Dacura: A new solution to data harvesting and knowledge extraction for the historical sciences
File Type:
PDFItem Type:
Journal ArticleDate:
2018Author:
Access:
openAccessCitation:
Peregrine, P.N., Brennan, R., Currie, T., Feeney, K., François, P., Turchin, P. & Whitehouse, H., Dacura: A new solution to data harvesting and knowledge extraction for the historical sciences, Historical Methods: A Journal of Quantitative and Interdisciplinary History, 51, 3, 2018, 165 - 174Download Item:
Abstract:
New advances in computer science address problems historical scientists face in gathering and evaluating the now vast data sources available through the Internet. As an example we introduce Dacura, a dataset curation platform designed to assist historical researchers in harvesting, evaluating, and curating high-quality information sets from the Internet and other sources. Dacura uses semantic knowledge graph technology to represent data as complex, inter-related knowledge allowing rapid search and retrieval of highly specific data without the need of a lookup table. Dacura automates the generation of tools to help non-experts curate high quality knowledge bases over time and to integrate data from multiple sources into its curated knowledge model. Together these features allow rapid harvesting and automated evaluation of Internet resources. We provide an example of Dacura in practice as the software employed to populate and manage the Seshat databank.
URI:
https://www.tandfonline.com/doi/full/10.1080/01615440.2018.1443863http://hdl.handle.net/2262/91233
Sponsor
Grant Number
Economic and Social Research Council (ESRC)
RES-060-25-0085
European Commission
644055
John Templeton Foundation
Author's Homepage:
http://people.tcd.ie/rbrennaDescription:
PUBLISHED
Author: BRENNAN, ROB; Peregrine, Peter N.; Currie, Thomas; Feeney, Kevin; François, Pieter; Turchin, Peter; Whitehouse, Harvey
Type of material:
Journal ArticleURI:
https://www.tandfonline.com/doi/full/10.1080/01615440.2018.1443863http://hdl.handle.net/2262/91233
Collections
Series/Report no:
Historical Methods: A Journal of Quantitative and Interdisciplinary History;51;
3;
Availability:
Full text availableSubject (TCD):
Digital Humanities , SEMANTIC WEBDOI:
10.1080/01615440.2018.1443863Metadata
Show full item recordLicences: