Treffer: The impact of a large language model-based programming learning environment on students' motivation and programming ability.

Attention to programming education from K-12 to higher education has been growing with the aim of fostering students' programming ability. This ability involves employing appropriate algorithms and computer codes to solve problems and can be enhanced through practical learning. However, in a formal educational setting, it is challenging to provide personalized support to students during their practice owing to limited teacher availability and large class sizes. The integration of large language model-based programming learning environments (LPLEs) is a promising approach to this issue as this setting supports adaptive learning by providing feedback on student codes and responses to questions with human-like interactions. However, a research gap exists regarding the efficacy of LPLEs. To address this gap, this study integrated an LPLE for first-year high school students in South Korea engaged in learning programming for the first time as part of the national curriculum. We examined the impact of the LPLE using a mixed-methods approach with a quasi-experimental design through the lens of self-determination theory. We also investigated students' learning behaviors within the LPLE and their perceptions of how specific elements of the LPLE satisfy their basic psychological needs. The results provide evidence that the LPLE supports students' basic psychological needs, enhances autonomous motivation, and improves programming ability. Based on these findings, implications regarding effective utilization and development of the LPLE are discussed from a theoretical and practical perspective. [ABSTRACT FROM AUTHOR]

Copyright of Education & Information Technologies is the property of Springer Nature 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.)