Preliminary Practices for Java Programming Tools and TDD Courses Utilizing Generative AI and Online Education

Authors

  • Mika Ohtsuki Saga University
  • Tetsuro Kakeshita Saga University

DOI:

https://doi.org/10.52731/liir.v006.388

Keywords:

Programming education, GitHub Copilot, Object-oriented programming, Test-Driven Development

Abstract

With the rapid advancement of generative AI, automation is increasingly being introduced across various stages of software development. In response to these changes, programming education must also evolve to incorporate the use of generative AI from the outset. In this study, we designed and implemented intermediate-level programming courses that integrate generative AI tools such as GitHub Copilot. The curriculum consisted of three subjects: Object-Oriented Programming, Test-Driven Development, and Practical Project Development. Each course combined on-demand instructional materials with AI-assisted exercises. As a result, learners reported high levels of satisfaction and frequently accessed course materials and assessments. Notably, many students demonstrated the ability to critically evaluate and adapt AI-generated suggestions rather than relying on them uncritically. A comparative survey between GitHub Copilot and Google Gemini revealed that students were also beginning to select AI tools based on purpose and context. These findings indicate the potential of educational designs that foster practical programming skills and cultivate AI literacy. This initiative highlights the promise of programming education that is both AI-integrated and personalized, offering new directions for curriculum innovation in higher education.

References

M. Daun and J. Brings, “How ChatGPT Will Change Software Engineering Educa-tion,” in Proc. ITiCSE, 2023, pp. 110–116.

OpenAI, “ChatGPT.”; Available: https://chatgpt.com/

GitHub Inc., “GitHub Copilot.”; Available: https://docs.github.com/ja/copilot

P. Haindl and G. Weinberger, “Students’ Experiences of Using ChatGPT in an Undergraduate Programming Course,” IEEE Access, vol. 12, pp. 43519–43529, 2024.

M. Hu, T. Assadi, and H. Mahroeian, “Explicitly Introducing ChatGPT into First-year Programming Practice: Challenges and Impact,” in Proc. TALE, IEEE, 2023.

M. Kazemitabaar et al., “Studying the Effect of AI Code Generators on Supporting Novice Learners in Introductory Programming,” in Proc. CHI, ACM, 2023, pp. 1–23.

B. Bull and A. Kharrufa, “Generative AI Assistants in Software Development Ed-ucation,” arXiv preprint, arXiv:2303.13936, 2023.

M. M. Rahman and Y. Watanobe, “ChatGPT for Education and Research: Oppor-tunities, Threats, and Strategies,” Applied Sciences, vol. 13, no. 9, p. 5783, 2023.

J. Leinonen et al., “Using Large Language Models to Enhance Programming Error Messages,” in Proc. SIGCSE, ACM, 2023, pp. 563–569.

J. Prather et al., “It's Weird That it Knows What I Want": Usability and Interactions with Co-pilot for Novice Programmers,” arXiv preprint, arXiv:2304.02491, 2023.

J. Prather et al., “Beyond the Hype: A Comprehensive Review of Current Trends in Generative AI Research, Teaching Practices, and Tools,” arXiv preprint, arXiv:2412.14732, 2024.

Western Governors University, “How AI Is Reshaping Curriculum Design: Insights for Future Educators,” WGU Blog, 2025; https://www.wgu.edu/blog/how-ai-reshaping-curriculum-design-insights-future-educators2412.html

Axios, “Northeastern University joins AI-higher ed experiment,” Axios Local Boston, Apr. 3, 2025; https://www.axios.com/local/boston/2025/04/03/northeastern-ai-claude-partnership

K. Beck, Test-Driven Development: By Example, Addison-Wesley, 2002.

K. Beck, “Embracing change with extreme programming,” IEEE Computer, Vol. 32, No. 10, pp. 70-77, 1999.

J. H. Flavell, “Metacognition and cognitive monitoring: A new area of cogni-tive-developmental inquiry,” American Psychologist, vol. 34, no. 10, pp. 906–911, 1979.

Cline Project, "Cline," GitHub; Available: https://github.com/cline

Downloads

Published

2025-10-03