ATTENTION/WARNING - NE PAS DÉPOSER ICI/DO NOT SUBMIT HERE

Ceci est la version de TEST de DIAL.mem. Veuillez ne pas soumettre votre mémoire sur ce site mais bien à l'URL suivante: 'https://thesis.dial.uclouvain.be'.
This is the TEST version of DIAL.mem. Please use the following URL to submit your master thesis: 'https://thesis.dial.uclouvain.be'.
 

Applying ChatGPT to CS1 programming course

Vaillant, Manu ; Meza Semet, Louis
(2024)

Files

Vaillant_56192100_MezaSemet_29911800_2024.pdf
  • UCLouvain restricted access
  • Adobe PDF
  • 2.11 MB

Details

Supervisors
Pecheur, Charles ; Mens, Kim
Faculty
Ecole polytechnique de Louvain
Degree label
Master [120] en sciences informatiques, à finalité spécialisée
Abstract
The rapid growth of artificial intelligence, particularly in natural language processing, offers new opportunities for educational tools. This thesis explores the potential of ChatGPT in the context of an introductory programming course. The motivation for this study was to explore the possibilities of ChatGPT and to see what could be achieved within the CS1 (Computer Science 1st year) course. In a survey conducted among the students taking this course, we noted a high level of use of AI tools, which makes this work even more meaningful. The main problem covered is the evaluation of ChatGPT's effectiveness in generating correct and efficient code solutions for CS1 programming exercises and exams. The study involved a comprehensive evaluation of ChatGPT's performance on a diverse set of programming problems sourced from the LINFO1101 course, covering various levels of difficulty. This work also includes an analysis of the tool's performance in generating unit tests that can be used to correct source code written by students. This work provides empirical evidence of ChatGPT's strengths and limitations for the CS1 programming course. It offers insights into best practices for using AI tools in learning and identifies areas for future research. The thesis demonstrates that while ChatGPT shows promise as an educational tool, significant challenges remain. The knowledge acquired is laying the foundations for new innovations in AI-assisted education, with the aim of making learning more accessible and more effective for students.