Embedding-based Automated Assessment of Domain Models

Domain modeling is an essential component in many software engineering courses since it serves as a way to represent and understand the concepts and relationships in a problem domain. Course instructors evaluate student-generated diagrams manually, comparing them against a reference solution and providing feedback. However, as enrollment in software engineering courses continues to rise, manual grading of a large number of student submissions becomes an overwhelming and time-intensive task for instructors. Hence, there is a need for automated assessment of domain models which assists course instructors during the grading process. In this paper, we propose a novel text embedding-based approach that automatizes the assessment of domain models expressed in a textual domain-specific language, against reference solutions created by modeling experts. Our algorithm showcases remarkable proficiency in matching model elements across domain models, achieving an F1-score of 0.82 for class matching, 0.75 for attribute matching, and 0.80 for relation matching. Our algorithm also yields grades highly correlated with human grader assessments, with correlations exceeding 0.8 and mean absolute errors below 0.05.