Assessing UML Models by ChatGPT: Implications for Education

In software engineering (SE) research and practice, UML is well known as an essential modeling methodology for requirements analysis and software modeling in both academia and industry. In particular, fundamental knowledge of UML modeling and practice in creating high-quality UML models are included in SE-relevant courses in the undergraduate programs of many universities. This leads to a time-consuming and labor-intensive task for educators to review and grade a large number of UML models created by the students. Recent advancements in generative AI techniques, such as ChatGPT, have paved new ways to automate many SE tasks. However, current research or tools seldom explore the capabilities of ChatGPT in evaluating the quality of UML models. This paper aims to investigate the feasibility and effectiveness of ChatGPT in assessing the quality of UML use case diagrams, class diagrams, and sequence diagrams. First, 11 evaluation criteria with grading details were proposed for these UML models. Next, a series of experiments were designed and conducted on 40 students' UML modeling reports to explore the performance of ChatGPT in evaluating and grading these UML diagrams. The research findings reveal that ChatGPT performed well in this assessing task because the scores that ChatGPT gives to the UML models are similar to the ones by human experts, and there are three evaluation discrepancies between ChatGPT and human experts, but varying in different evaluation criteria used in different types of UML models.