Exercisify: An AI-Powered Statement Evaluator

Author Ricardo Queirós



PDF
Thumbnail PDF

File

OASIcs.ICPEC.2024.19.pdf
  • Filesize: 0.52 MB
  • 6 pages

Document Identifiers

Author Details

Ricardo Queirós
  • School of Media Arts and Design & CRACS - INESC TEC, Polytechnic University of Porto, Portugal

Cite AsGet BibTex

Ricardo Queirós. Exercisify: An AI-Powered Statement Evaluator. In 5th International Computer Programming Education Conference (ICPEC 2024). Open Access Series in Informatics (OASIcs), Volume 122, pp. 19:1-19:6, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
https://doi.org/10.4230/OASIcs.ICPEC.2024.19

Abstract

A growing concern with current teaching approaches underscores the need for innovative paradigms and tools in computer programming education, aiming to address disparate user profiles, enhance engagement, and cultivate deeper understanding among learners This article proposes an innovative approach to teaching programming, where students are challenged to write statements for solutions automatically generated. With this approach, rather than simply solving exercises, students are encouraged to develop code analysis and problem formulation skills. For this purpose, a Web application was developed to materialize these ideas, using the OpenAI API to generate exercises and evaluate statements written by the students. The transformation of this application in H5P and its integration in a LMS gamified workflow is explored for wider and more effective adoption.

Subject Classification

ACM Subject Classification
  • Social and professional topics → Computer science education
Keywords
  • Code generation
  • Computer Programming
  • Gamification

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads

References

  1. Yannik Bauer, José Paulo Leal, and Ricardo Queirós. Can a Content Management System Provide a Good User Experience to Teachers? In 4th International Computer Programming Education Conference (ICPEC 2023), volume 112 of Open Access Series in Informatics (OASIcs), pages 4:1-4:8, Dagstuhl, Germany, 2023. Schloss Dagstuhl - Leibniz-Zentrum für Informatik. Google Scholar
  2. Ghader Kurdi, Jared Leo, Bijan Parsia, Uli Sattler, and Salam Al-Emari. A systematic review of automatic question generation for educational purposes. International Journal of Artificial Intelligence in Education, 30, 2019. Google Scholar
  3. José Carlos Paiva, Ricardo Queirós, José Paulo Leal, Jakub Swacha, and Filip Miernik. Managing gamified programming courses with the FGPE platform. Information, 13(2):45, 2022. Google Scholar
  4. Niko Strijbol, Charlotte Van Petegem, Rien Maertens, Boris Sels, Christophe Scholliers, Peter Dawyndt, and Bart Mesuere. Tested - an educational testing framework with language-agnostic test suites for programming exercises. SoftwareX, 22:101404, 2023. Google Scholar
  5. Nguyen Binh Duong Ta, Hua Gia Phuc Nguyen, and Gottipati Swapna. Exgen: Ready-to-use exercise generation in introductory programming courses. In Proceedings of the 31st International Conference on Computers in Education Conference, pages 1-10, Matsue, Shimane, Japan, december 4-8 2023. Google Scholar
  6. Laura Zavala and Benito Mendoza. On the use of semantic-based aig to automatically generate programming exercises. In Proceedings of the 49th ACM Technical Symposium on Computer Science Education, SIGCSE '18, pages 14-19, New York, NY, USA, 2018. Association for Computing Machinery. Google Scholar
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail