ShExML: improving the usability of heterogeneous data mapping languages for first-time users

Integration of heterogeneous data sources in a single representation is an active field with many different tools and techniques. In the case of text-based approaches those that base the definition of the mappings and the integration on a DSL-there is a lack of usability studies. In this work we have conducted a usability experiment (n = 17) on three different languages: ShEXML (our own language), YARRRML and SPARQL-Generate. Results show that ShEXML users tend to perform better than those of YARRRML and SPARQL-Generate. This study sheds light on usability aspects of these languages design and remarks some aspects of improvement.