Work

Using Generative AI in Higher Programming Education: An Empirical Evaluation

Year: 2026
Type: conference-paper
Abstract: The growing use of generative artificial intelligence (GenAI) tools like ChatGPT presents both opportunities and challenges for programming education, especially for novices. While these tools can assist with code generation, debugging and conceptual understanding, there is a risk that they will promote superficial learning and the uncritical adoption of generated code. This paper presents the development and empirical evaluation of a best-practice guideline designed to support students in the reflective and effective use of generative AI in programming contexts. We conducted an experimental study with 36 first-semester computer science students, comparing a control group using AI without guidance against an experimental group equipped with our structured guide. The results show that while the quantitative performance metrics remained similar between the groups, the students using the guideline demonstrated a significantly higher self-reported understanding of their solutions and exhibited more reflective AI interaction patterns. Observational data revealed that guided users critically evaluated (66.7% vs 55.6%), modified (61.1% vs 22.2%), and rejected (38.9% vs 16.7%) AI-generated suggestions more frequently. A supplementary AI guidance workshop conducted provided convergent validation: students independently identified debugging and conceptual understanding as their primary skill gaps requiring AI support.
Language: English
Open Access status: hybrid
OpenAlex ID: W7161961719
FWCI:
Cites:
Cited by:
Related to: 10