2 Search Results for "Nagy, Csaba"

Document
DOI: 10.4230/OASIcs.ICPEC.2025.7
A Generative Artificial Intelligence Tool to Correct Programming Exercises

Authors: Filipe Portela

Published in: OASIcs, Volume 133, 6th International Computer Programming Education Conference (ICPEC 2025)

Abstract
This paper presents an innovative strategy for assessing programming exercises in higher education, leveraging generative artificial intelligence (GAI) to support automated grading while ensuring transparency, fairness, and pedagogical relevance. The proposed approach is framed within the TechTeach paradigm and integrates multiple tools - HackerRank for code development, Google Forms and Sheets for submission and prompt generation, and the ChatGPT API for intelligent evaluation. The correction process is personalised using student-specific variables (e.g., student ID, birth date, performance in group work), which are dynamically embedded into the statement and prompt. The GAI algorithm evaluates the code and performs authorship verification using peer-assessed effort data, enabling the detection of potential plagiarism or misuse of AI tools. A case study was conducted in the 2023/2024 edition of the Web Programming course at the University of Minho, which involved 118 students. Results indicate that the method produced consistent and meaningful grades, reflecting a balanced perception of difficulty from students. The system also includes a gamification mechanism (Grade Rescue) for managing contested cases. The achieved findings (>90% of students approved the exercise model) support the viability of GAI-based evaluation as a scalable and effective solution for programming education, while maintaining academic integrity and enhancing the student experience.
Cite as

Filipe Portela. A Generative Artificial Intelligence Tool to Correct Programming Exercises. In 6th International Computer Programming Education Conference (ICPEC 2025). Open Access Series in Informatics (OASIcs), Volume 133, pp. 7:1-7:16, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@InProceedings{portela:OASIcs.ICPEC.2025.7,
  author =	{Portela, Filipe},
  title =	{{A Generative Artificial Intelligence Tool to Correct Programming Exercises}},
  booktitle =	{6th International Computer Programming Education Conference (ICPEC 2025)},
  pages =	{7:1--7:16},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-393-5},
  ISSN =	{2190-6807},
  year =	{2025},
  volume =	{133},
  editor =	{Queir\'{o}s, Ricardo and Pinto, M\'{a}rio and Portela, Filipe and Sim\~{o}es, Alberto},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.ICPEC.2025.7},
  URN =		{urn:nbn:de:0030-drops-240376},
  doi =		{10.4230/OASIcs.ICPEC.2025.7},
  annote =	{Keywords: TechTeach, Information Systems, Higher Education, Generative AI, Code Exercises}
}
Document
Pearl/Brave New Idea
DOI: 10.4230/LIPIcs.ECOOP.2023.43
On the Rise of Modern Software Documentation (Pearl/Brave New Idea)

Authors: Marco Raglianti, Csaba Nagy, Roberto Minelli, Bin Lin, and Michele Lanza

Published in: LIPIcs, Volume 263, 37th European Conference on Object-Oriented Programming (ECOOP 2023)

Abstract
Classical software documentation, as it was conceived and intended decades ago, is not the only reality anymore. Official documentation from authoritative and official sources is being replaced by real-time collaborative platforms and ecosystems that have seen a surge, influenced by changes in society, technology, and best practices. These modern tools influence the way developers document the conception, design, and implementation of software. As a by-product of these shifts, developers are changing their way of communicating about software. Where once official documentation stood as the only truth about a project, we now find a multitude of volatile and heterogeneous documentation sources, forming a complex and ever-changing documentation landscape. Software projects often include a top-level README file with important information, which we leverage to identify their documentation landscape. Starting from ∼12K GitHub repositories, we mine their README files to extract links to additional documentation sources. We present a qualitative analysis, revealing multiple dimensions of the documentation landscape (e.g., content type, source type), highlighting important insights. By analyzing instant messaging application links (e.g., Gitter, Slack, Discord) in the histories of README files, we show how this part of the landscape has grown and evolved in the last decade. Our findings show that modern documentation encompasses communication platforms, which are exploding in popularity. This is not a passing phenomenon: On the contrary, it entails a number of unknowns and socio-technical problems the research community is currently ill-prepared to tackle.
Cite as

Marco Raglianti, Csaba Nagy, Roberto Minelli, Bin Lin, and Michele Lanza. On the Rise of Modern Software Documentation (Pearl/Brave New Idea). In 37th European Conference on Object-Oriented Programming (ECOOP 2023). Leibniz International Proceedings in Informatics (LIPIcs), Volume 263, pp. 43:1-43:24, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)

Copy BibTex To Clipboard

@InProceedings{raglianti_et_al:LIPIcs.ECOOP.2023.43,
  author =	{Raglianti, Marco and Nagy, Csaba and Minelli, Roberto and Lin, Bin and Lanza, Michele},
  title =	{{On the Rise of Modern Software Documentation}},
  booktitle =	{37th European Conference on Object-Oriented Programming (ECOOP 2023)},
  pages =	{43:1--43:24},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-281-5},
  ISSN =	{1868-8969},
  year =	{2023},
  volume =	{263},
  editor =	{Ali, Karim and Salvaneschi, Guido},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ECOOP.2023.43},
  URN =		{urn:nbn:de:0030-drops-182369},
  doi =		{10.4230/LIPIcs.ECOOP.2023.43},
  annote =	{Keywords: software documentation landscape, GitHub README, instant messaging}
}
  • Refine by Type
  • 2 Document/PDF
  • 1 Document/HTML

  • Refine by Publication Year
  • 1 2025
  • 1 2023

  • Refine by Author
  • 1 Lanza, Michele
  • 1 Lin, Bin
  • 1 Minelli, Roberto
  • 1 Nagy, Csaba
  • 1 Portela, Filipe
  • Show More...

  • Refine by Series/Journal
  • 1 LIPIcs
  • 1 OASIcs

  • Refine by Classification
  • 1 Human-centered computing → Collaborative and social computing
  • 1 Information systems → Information retrieval
  • 1 Software and its engineering → Collaboration in software development

  • Refine by Keyword
  • 1 Code Exercises
  • 1 Generative AI
  • 1 GitHub README
  • 1 Higher Education
  • 1 Information Systems
  • Show More...

Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2026 Schloss Dagstuhl – LZI GmbH Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact