Utilizing Adaptive Learning with GPT-4 for Introduction to Python: Effects on Accuracy and Time-to-Solution
Received: 8 July 2025 | Revised: 16 August 2025, 18 September 2025, and 30 September 2025 | Accepted: 12 October 2025 | Online: 9 February 2026
Corresponding author: Lenis Wong
Abstract
Programming instruction in universities often struggles to adapt to individual needs and sustain motivation. This study presents Code Showdown, a web application that combines adaptive learning with GPT-4 to strengthen Python programming skills through automatically generated challenges and immediate personalized feedback. The development followed four phases: (i) selecting the pedagogical approach, (ii) choosing the language model, (iii) integrating GPT-4 for challenge generation and formative feedback, and (iv) building a scalable web architecture. The proposed approach was evaluated with 40 undergraduates (two groups of 20 individuals) over two weeks. Group E1 studied with traditional resources, whereas Group E2 used Code Showdown in individual and multiplayer modes. Using explicit metrics—Improvement Score (IS, %) and Improvement in Response Time (IRT, %)—Group E2 achieved higher means across difficulty levels: IS of 18.9±4.2% (Easy), 40.7±4.7 % (Intermediate), and 58.6±5.1 % (Hard), and IRT reductions of 32.4±6.3%, 28.0±5.8%, and 28.3±6.1 %, respectively. A t-test showed that these differences were statistically significant (p<0.05). Satisfaction was high (ISO/IEC 25010-based survey), with more than 80% positive ratings and a recommendation score of 4.9±0.3/5. These findings suggest that adaptive, GPT-4-assisted practice may enhance accuracy and efficiency in introductory Python while maintaining engagement through gamification and real-time competition.
Keywords:
programming skills, ChatGPT/GPT-4, adaptive learning, gamification, AI in educationDownloads
References
I. Cingillioglu, U. Gal, and A. Prokhorov, "AI-experiments in education: An AI-driven randomized controlled trial for higher education research," Education and Information Technologies, vol. 29, no. 15, pp. 19649–19677, Oct. 2024. DOI: https://doi.org/10.1007/s10639-024-12633-y
Y. Jing, H. Wang, X. Chen, and C. Wang, "What factors will affect the effectiveness of using ChatGPT to solve programming problems? A quasi-experimental study," Humanities and Social Sciences Communications, vol. 11, no. 1, Feb. 2024, Art. no. 319. DOI: https://doi.org/10.1057/s41599-024-02751-w
K. Hartley, M. Hayak, and U. H. Ko, "Artificial Intelligence Supporting Independent Student Learning: An Evaluative Case Study of ChatGPT and Learning to Code," Education Sciences, vol. 14, no. 2, Jan. 2024, Art. no. 120. DOI: https://doi.org/10.3390/educsci14020120
D. López-Fernández, A. Gordillo, R. Lara-Cabrera, and J. Alegre, "Comparing effectiveness of educational video games of different genres in computer science education," Entertainment Computing, vol. 47, Aug. 2023, Art. no. 100588. DOI: https://doi.org/10.1016/j.entcom.2023.100588
B. Idrisov and T. Schlippe, "Program Code Generation with Generative AIs," Algorithms, vol. 17, no. 2, Jan. 2024, Art. no. 62. DOI: https://doi.org/10.3390/a17020062
J. San Martin, W. Romero, J. L. Castillo-Sequera, and L. Wong, "Talki: A Mobile Application to Improve English Learning of High School Students in Peru utilizing Virtual Reality and Gamification," Engineering, Technology & Applied Science Research, vol. 14, no. 5, pp. 17472–17481, Oct. 2024. DOI: https://doi.org/10.48084/etasr.8223
O. Dieste, E. R. Fonseca, G. Raura, and P. Rodríguez, "Efectividad del Test-Driven Development: Un Experimento Replicado," Revista Latinoamericana de Ingenieria de Software, vol. 3, no. 3, July 2015, Art. no. 141. DOI: https://doi.org/10.18294/relais.2015.141-147
T. Kosar, D. Ostojić, Y. D. Liu, and M. Mernik, "Computer Science Education in ChatGPT Era: Experiences from an Experiment in a Programming Course for Novice Programmers," Mathematics, vol. 12, no. 5, Feb. 2024, Art. no. 629. DOI: https://doi.org/10.3390/math12050629
F. Jiang and D. Shangguan, "Researching and designing educational games on the basis of ‘self-regulated learning theory,’" Frontiers in Psychology, vol. 13, Nov. 2022, Art. no. 996403. DOI: https://doi.org/10.3389/fpsyg.2022.996403
Q. Fu, Y. Zheng, M. Zhang, L. Zheng, J. Zhou, and B. Xie, "Effects of different feedback strategies on academic achievements, learning motivations, and self-efficacy for novice programmers," Educational technology research and development, vol. 71, no. 3, pp. 1013–1032, June 2023. DOI: https://doi.org/10.1007/s11423-023-10223-2
Y. Hanggara, A. Qohar, and Sukoriyanto, "The Impact of Augmented Reality-Based Mathematics Learning Games on Students’ Critical Thinking Skills," International Journal of Interactive Mobile Technologies (iJIM), vol. 18, no. 07, pp. 173–187, Apr. 2024. DOI: https://doi.org/10.3991/ijim.v18i07.48067
Y. Li, D. Chen, and X. Deng, "The impact of digital educational games on student’s motivation for learning: The mediating effect of learning engagement and the moderating effect of the digital environment," PLOS ONE, vol. 19, no. 1, Jan. 2024, Art. no. e0294350. DOI: https://doi.org/10.1371/journal.pone.0294350
C. G. Hidalgo Suarez, V. A. Bucheli-Guerrero, and H. A. Ordóñez-Eraso, "Artificial Intelligence and Computer-Supported Collaborative Learning in Programming: A Systematic Mapping Study," Tecnura, vol. 27, no. 75, pp. 175–206, Jan. 2023. DOI: https://doi.org/10.14483/22487638.19637
Downloads
How to Cite
License
Copyright (c) 2025 Diego Santivanez, Kevin Oliva, Lenis Wong
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
