Publications

Abstract: This paper introduces an advanced functionality designed to facilitate the learning of UML class diagram construction. Built upon an integrated Retrieval Augmented Generation Large Language Model, the functionality provides enriched feedback by leveraging accumulated knowledge. The functionality is implemented in an existing tool named UML Miner, a Visual Paradigm plugin that captures and analyzes student-generated UML diagrams by applying process mining techniques. By offering personalized feedback and continuous support during modeling, the tool aims to enhance learning outcomes and students’ engagement.

Abstract: This study introduces an innovative AI-powered scaffolding approach aimed at enhancing software modeling learning through UML diagrams. The focus of this research is on defining the principles and functions comprising the scaffolding. Leveraging recent advancements in generative AI, our approach provides a structured educational framework to improve comprehension and proficiency in modeling concepts. We present the initial implementation of the scaffolding, specifically highlighting the feedback function. By integrating theoretical insights with practical applications, this study seeks to advance Model-Driven Software Engineering education and underscores the potential of AI in enhancing instructional methodologies.

Abstract: Teaching the Unified Modelling Language (UML) is a critical task in the frame of Software Engineering courses. Teachers need to understand the students’ behavior along with their modeling activities to provide suggestions and feedback to avoid more frequent mistakes and improve their capabilities. This paper presents a novel approach for teaching the UML in Software Engineering courses, focusing on understanding and improving student behavior and capabilities during modeling activities. It introduces a cloud-based tool that captures and analyzes UML diagrams created by students during their interactions with a UML modeling tool. The key aspect of the proposal is the integration of a Retrieval Augmented Generation Large Language Model (RAG-based LLM), which generates insightful feedback for students by leveraging knowledge acquired during the modeling process.The effectiveness of this method is demonstrated through an experiment involving a substantial dataset comprising 5,120 labeled UML models. The validation process confirms the performance of the UML RAG-based LLM in providing relevant feedback related to entities and relationships in the students’ models. Additionally, a qualitative analysis highlights the user satisfaction, underscoring its potential as a valuable tool in enhancing the learning experience in software modeling education.

Abstract: Modeling is a key activity in conceptual design and system design, learning and understanding modeling languages such as the Unified Modeling Language (UML) is important. Current UML learning applications and gamification-based alternatives lack guidance for novice modelers regarding possible modeling activities. To overcome this problem, in this demo paper, we present a tool called UML Miner, implemented as a plug-in, that evaluates all UML diagrams realized in the Visual Paradigm environment. UML Miner records all modeling events used in a modeling software project as event logs. By analyzing event logs generated from the use of Visual Paradigm, UML Miner can perform conformance checking to provide useful tips to modelers. These tips are based on the UML model created by highly skilled modelers. In particular, UML Miner can compare different modeling process executions through conformance checking and identify behavioral similarities and differences. The goal of this approach is to improve learner motivation and increase learning outcomes.