R2RML defines a language to express mappings from relational data to RDF. That way, applications built on top of the W3C Semantic Technology stack can seamlessly integrate relational data. A major obstacle to using R2RML, though, is the effort for manually curating the mappings. In particular in scenarios that aim to map data from huge and complex relational schemata (e.g., [5]) to more abstract ontologies efficient ways to support the mapping creation are needed. In previous work we presented a mapping editor that aims to reduce the human effort in mapping creation [12]. While assisting users in mapping construction the editor imposed a fixed editing approach, which turned out to be not optimal for all users and all kinds of mapping tasks. Most prominently, it is unclear on which of the two data models users should best start with the mapping construction. In this paper, we present the results of a comprehensive user study that evaluates different alternative editing approaches for constructing R2RML mapping rules. The study measures the efficiency and quality of mapping construction to find out which approach works better for users with different background knowledge and for different types of tasks.
展开▼