Treffer: A Generative Artificial Intelligence (AI)-Based Human-Computer Collaborative Programming Learning Method to Improve Computational Thinking, Learning Attitudes, and  Learning Achievement.

Human-computer collaboration is an effective way to learn programming courses. However, most existing human-computer collaborative programming learning is supported by traditional computers with a relatively low level of personalized interaction, which greatly limits the efficiency of students' efficiency of programming learning and development of computational thinking. To address the above issues, this study introduces generative AI into human-computer collaborative programming learning and proposes a dialogue-negotiated human-computer collaborative programming learning method based on generative AI. The method focuses on the problems-solving process and constructs multiple agents through Prompt design, which enable students to improve their computational thinking and master programming skills in the process of human-computer interaction for problem-solving. Finally, a quasi-experiment was conducted to verify the effectiveness of the proposed method in a 10th grade computer programming course in a high school. 43 students in the experimental group learned with the proposed method, while 42 students in the control group adopted the traditional computer-supported human-computer collaborative programming learning method. The experimental results showed that the proposed method more significantly improved students' computational thinking, programming learning attitudes, and learning achievement. This study provides theoretical foundations and application reference for future generative AI-assisted human-computer collaborative teaching. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Educational Computing Research is the property of Sage Publications Inc. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)