A comparison of object-triple mapping libraries

Article type: Research Article

Authors: Ledvinka, Martin^{; *} | Křemen, Petr

Affiliations: Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague, Technická 2, 166 27 Prague 6 – Dejvice, Czech Republic. E-mails: martin.ledvinka@fel.cvut.cz, petr.kremen@fel.cvut.cz

Correspondence: [*] Corresponding author. E-mail: martin.ledvinka@fel.cvut.cz.

Abstract: Domain-independent information systems like ontology editors provide only limited usability for non-experts when domain-specific linked data need to be created. On the contrary, domain-specific applications require adequate architecture for data authoring and validation, typically using the object-oriented paradigm. So far, several software libraries mapping the RDF model (representing linked data) to the object model have been introduced in the literature. In this paper, we develop a novel framework for comparison of object-triple mapping solutions in terms of features and performance. For feature comparison, we designed a set of qualitative criteria reflecting object-oriented application developer’s needs. For the performance comparison, we introduce a benchmark based on a real-world information system that we implemented using one of the compared object-triple mapping (OTM) solutions – JOPA. We present a detailed evaluation of a selected set of OTM libraries, showing how they differ in terms of features. We further narrow down the set of selected OTM libraries to contain only RDF4J-compatible ones and use the benchmark to measure their time and memory efficiency.

Keywords: Object-triple mapping, object-ontological mapping, object-oriented programming, RDF, benchmark

DOI: 10.3233/SW-190345

Journal: Semantic Web, vol. 11, no. 3, pp. 483-524, 2020