A Systematic Literature Review of the Practical Applications of Artificial Intelligence-Generated Content (AIGC) Using OpenAI ChatGPT, Copilot, and Codex in Programming Education
This systematic literature review investigated the practical applications of Artificial Intelligence-Generated Content (AIGC) tools, specifically ChatGPT, Copilot, and Codex, in programming education. The review synthesized current research trends and key applications, with a particular focus on large language models (LLMs) and advanced chatbots. The findings revealed a significant increase in research interest following the release of ChatGPT, with most studies concentrating on university-level programming education. The review identified eight primary applications of AIGC tools in programming education, including evaluating AI performance in solving programming tasks, providing AI-driven code generation and assistance, automating assessment review and feedback, delivering personalized learning and tutoring, supporting educators and instructional design, investigating educator and student perceptions, checking for plagiarism, and exploring AI's impact on curriculum design. Despite the promising potential of these tools, critical gaps remained, particularly in primary and secondary education, as well as in online and blended learning environments. Future research was recommended to address these areas and to explore a broader range of AIGC tools to unlock their full potential for enhancing programming education.
Authors
- Wan Chong Choi (ORCID: https://orcid.org/0000-0002-8415-6998)
- Iek Chong Choi (ORCID: https://orcid.org/0009-0000-0241-7166)
- Chun‐Ming Chang
- Huan‐Yao Lei
Institutions
- Illinois Institute of Technology (US)
- Golden Gate University (US)
- Macao Polytechnic University (MO)
- City University of Macau (MO)
- University of Hong Kong (HK)
Publication Details
- Published
- 2024-11-23
- DOI
- https://doi.org/10.1145/3719487.3719519
- Citations
- 3
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.36