Ontology‐based model‐driven development of a destination management portal: Experience and lessons learned. (4th May 2018)

• Record Type: Journal Article
• Authors: Mili, Hafedh; Valtchev, Petko; Szathmary, Laszlo; Boubaker, Anis; Leshob, Abderrahmane; Charif, Yasmine; Martin, Louis
• Is Part Of: Software, practice & experience. Volume 48:Number 8(2018)
• Page Start: 1438
• Page End: 1460
• Publication Date: 2018-05-04
• Subjects: destination management portal -- experience report -- model‐driven engineering (MDE) -- ontology development -- web application engineering; Computer software -- Periodicals; Computer programming -- Periodicals; Computer programs -- Periodicals; 005.3
• DOI: 10.1002/spe.2581
• Languages: English
• ISSNs: 0038-0644

Abstract

Summary: We present a case study in model‐driven development of an e‐tourism portal that we chose to develop through generation from a domain model encoded as an ontology . We present (1) the requirements of e‐tourism portal, which dictated its high‐level design; (2) the principles behind our implementation strategy, including the use of a domain ontology as a starting model within the context of a model‐driven transformational approach; (3) the ontology development process and the code generation strategy used; and (4) the lessons learned. In particular, we compare our experiences to those reported in the model‐driven engineering (MDE) literature along 3 dimensions, ie, (1) the impact of MDE on the development process, (2) the choice of the modeling approach, and (3) the impact of code generation on design and code quality and testing. Overall, our experiences corroborated some of the theoretical claims and many of the practical experiences with MDE. Key findings include (1) model‐driven development makes maintenance, not development, more efficient; (2) it does require a higher skill level than traditional development; (3) clients and managers need to be educated into what incrementality means in a generative approach ; (4) UML is neither necessary nor sufficient to handle the required representational flexibility; (5) it is difficult to build models that are good for both human consumption and code generation; and (6) it is difficult to generate code that is, simultaneously, efficient, pretty, and easy to maintain. We conclude by summarizing the findings of the paper.