Towards Machine Learning for Learnability of MDD Tools

Saad bin Abid, Vishal Mahajan und Levi Lúcio

Software Engineering and Knowledge Engineering (SEKE) Conference, Lisbon, Portugal, pp. 1–6

Juli 2019 · DOI: 10.18293/SEKE2019-050


Learning how to build software systems using new tools can be a daunting task to anyone new to the job. This is especially true of tools that provide a large number of functionalities and views on the system under development, such as IDES for Model-Driven Development (MDD). Applying Machine Learning (ML) techniques can help in this state of affairs by pointing out to appropriate next actions to rookie or even intermediate developers. AutoFOCUS3 (AF3) is a mature MDD tool we are building in-house and for which we provide regular tutorials to new users. These users come from both the academia (e.g, students/professors) and the industry (e.g. managers/software engineers). Nonetheless, AF3 remains a complex tool and we have found there is a need to speedup the learning curve of the tool for students that attend our tutorials-or alternatively and more importantly for others that simply download the tool and attempt using it without human supervision. In this paper, we describe a machine learning-based recommendation system named MAGNET for aiding beginner and intermediate users of AF3 in learning the tool. We describe how we have gathered data and trained an ML model to suggest new commands, how a recommender system was integrated in the AF3, experiments we have run thus far, and the future directions of our work.

Stichworte: Model-Driven Development, MDD, AutoFOCUS3, Machine Learning, Intelligent Recommendation Systems, IRS, Eclipse IDE, Domain-Specific Languages, DSLs, development interaction data, methodology, tooling, model-based systems engineering, MbSE