Bringing Machine Learning to Automated Assessment of Programming Assignments

Dear Colleagues,

Learning how to program requires intense and diverse hands-on practice, supported by timely, accurate, and personalized feedback to enable progression after facing learning barriers and improve coding skills. Manual grading of programming assignments is a time-consuming and subjective process, which hinders its use in these contexts. Thus, automated assessment is an essential asset in programming education. These systems can analyze code syntax, logic, and execution, and offer insights into areas for improvement, potential bugs, and best coding practices. Machine learning (ML) brings the ability to adapt and personalize feedback based on individual student needs to automated assessment. By training the models on vast amounts of programming data, ML models can learn patterns and common errors made by students, enabling them to provide targeted feedback tailored to each learner. This personalized approach not only helps students understand their mistakes but also guides them towards specific areas of improvement, fostering a more efficient and effective learning experience. However, ensuring the reliability and fairness of automated grading systems is crucial. Models need to be trained on diverse datasets, encompassing different programming languages, problem domains, and difficulty levels, to mitigate biases and ensure accurate evaluation. Furthermore, transparency and interpretability of machine learning models are paramount, as educators and students alike need to understand how the assessment process works and trust its outcomes.

The aim of this Special Issue is to collect high-quality submissions on research bringing machine learning to automated assessment of programming assignments. Research outcomes presenting novel ML techniques and tools to automatically generate feedback or improve other aspects of the automated assessment of programming assignments are welcome. Additionally, discussing the challenges associated with fairness, bias, and interpretability and present strategies to address them is also within the scope of this work.

Dr. José Carlos Paiva
Dr. José Paulo Leal
Dr. Alvaro Figueira
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Information is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• automated assessment
• programming assignments
• machine learning
• feedback