• Corpus ID: 207969579

Towards Automated Grading of UML Class Diagrams with Machine Learning

  title={Towards Automated Grading of UML Class Diagrams with Machine Learning},
  author={Dave R. Stikkolorum and Peter van der Putten and Caroline Sperandio and Michel R. V. Chaudron},
This paper describes an exploratory study on the application of machine learning for the grading of UML class diagrams. Bachelor student pairs performed a software design task for learning software design with the use of UML class diagrams. After experts had manually graded the diagrams, we trained a regression model and multiple classification models. Based on the results we conclude that prediction of a 10 point grading scale can’t be done reliably. Classifying with trained data using expert… 

Figures and Tables from this paper

A Tool to Automate Student UML diagram Evaluation
A java-based tool is presented based on a simple yet effective algorithm developed by the authors that will read student and tutors solution diagrams as inputs and evaluate and grade the diagrams automatically and contributes towards automating UML diagram evaluations.
What's the grade of your diagram?: towards a streamlined approach for grading UML diagrams
The UMLGrade is an initial proposal to streamline the process of grading UML diagrams and seeks to enhance the learning of UML models through assessment reports considering semantic, syntactic aspects, design rules, readability, and object-oriented principles.
Automatic Generation and Marking of UML Database Design Diagrams
A system for the automatic creation and real-time evaluation of database design questions using UML diagrams and a classroom evaluation demonstrates high student satisfaction compared to traditional UML design questions and preference for using the software to improve their learning outcomes.
Exploring Feedback and Gamification in a Data Modeling Learning Tool
Data modeling is an essential part of IT studies. Learning how to design and structure a database is important when storing data in a relational database and is common practice in the IT industry.
Enhancing software model encoding for feature location approaches based on machine learning techniques
The results show that the best encoding and the best machine learning technique were compared to two traditional approaches that have been widely applied for feature location as well as for traceability link recovery and bug localization.
Is automated grading of models effective?: assessing automated grading of class diagrams
Empirically evaluates the efficacy of one such automated grading approach when applied in two real world settings: a beginner undergraduate class required to create an object-oriented design model, and an advanced undergraduate class elaborating a domain model.


UMLGrader: an automated class diagram grader
We present UMLGrader, a system designed to provide automated feedback to students on class diagrams written in the Unified Modeling Language (UML). Given a diagram which is constructed to model a
Automated Grading of Class Diagrams
  • Weiyi Bian, Omar Alam, J. Kienzle
  • Computer Science
    2019 ACM/IEEE 22nd International Conference on Model Driven Engineering Languages and Systems Companion (MODELS-C)
  • 2019
A metamodel is proposed that establishes mappings between the instructor solution and all the solutions for a class and uses a grading algorithm that uses syntactic, semantic and structural matching to match a student's solutions with the template solution.
UMLint: Identifying Defects in UML Diagrams
The checks made by UMLint are presented, the possible future directions are suggested, and a discussion about what standards should be expected of student-created models is invited.
Automated checks on UML diagrams
This paper presents an alternative technique for checking UML class diagrams based on graph queries which promises to be more flexible than the current approach which has drawbacks regarding flexibility.
A system to grade computer programming skills using machine learning
A system to grade computer programs automatically using a machine-learning based algorithm which determines closeness of the logic of the given program to a correct program and shows that the regression models provide much better grading than the ubiquitous test-case-pass based grading and rivals the grading accuracy of other open-response problems such as essay grading.
Revealing Students' UML Class Diagram Modelling Strategies with WebUML and LogViz
The most common strategies students use to create class designs are revealed: Depthless, Depth First, Breadth First and Ad Hoc, which indicates to support better layout and richness (detail).
Automated assessment of UML activity diagrams
This contribution presents an approach to dynamic checks of UML Activity Diagrams that makes use of trace generation and sequence alignment and shows fair results in preliminary experiments.
Providing Automated Feedback on Software Design for Novice Designers
A pedagogical feedback agent, designed to provide on-demand feedback on software design, was integrated with an online UML editor, and novice designers can design UML class diagrams within this environment and request formative feedback from the feedback agent.
Automated Grading of Java Assignments