Enriching Model Execution with Feedback to Support Testing of Semantic Conformance between Models and Requirements - Design and Evaluation of Feedback Automation Architecture

Model Driven Development (MDD) has traditionally been used to support model transformations and code generation. While plenty of techniques and tools are available to support modeling and transformations, tool support for checking the model quality in terms of semantic conformance with respect to the domain requirements is largely absent. In this work we present a model verification and validation approach based on model-driven feedback generation in a model-to-code transformation. The transformation is achieved using a single click. The generated output of the transformation is a compiled code which is achieved by a single click. This also serves as a rapid prototyping instrument that allows simulating a model (the terms prototyping and simulation are thus used interchangeably in the paper). The proposed feedback incorporation method in the generated prototype allows linking event execution in the generated code to its causes in the model used as input for the generation. The goal of the feedback is twofold: (1) to assist a modeler in validating semantic conformance of a model with respect to a domain to be engineered; (2) to support the learning perspective of less experienced modelers (such as students or junior analysts in their early career) by allowing them to detect modeling errors that result from the misinterpreted use of modeling language constructs. Within this work we focus on conceptual and platform independent models (PIM) that make use of two prominent UML diagrams – a class diagram (for modeling the structure of a system) and multiple interacting statecharts (for modeling a system’s dynamic behavior). The tool has been used in the context of teaching a requirements analysis and modeling course at KU Leuven. The proposed feedback generation technique has been constantly validated by means of “usability” evaluations, and demonstrates a high level of self-reported utility of the feedback. Additionally, the findings of our experimental studies also show a significant positive impact of feedback-enabled rapid prototyping method on semantic validation capabilities of novices. Despite our focus on specific diagramming techniques, the principles of the approach presented in this work can be used to support educational feedback automation for a broader spectrum of diagram types in the context of MDD and simulation.