A Smart ChatGPT Mobile Application for Improving C# Programming Skills for Students in Educational Institutions

Amira  Atta; Mona  Esmat; Nahed  Amasha; Eman  Elayat; W. K.  ElSaid

doi:10.48161/qaj.v5n2a1772

Authors

Amira Atta Computer Teacher Department, Faculty of Specific Education, Mansoura University, Mansoura 35516, Egypt.
Mona Esmat Computer Teacher Department, Faculty of Specific Education, Mansoura University, Mansoura 35516, Egypt.
Nahed Amasha Computer Teacher Department, Faculty of Specific Education, Mansoura University, Mansoura 35516, Egypt.
Eman Elayat Computer Teacher Department, Faculty of Specific Education, Mansoura University, Mansoura 35516, Egypt.
W. K. ElSaid Computer Teacher Department, Faculty of Specific Education, Mansoura University, Mansoura 35516, Egypt.

DOI:

https://doi.org/10.48161/qaj.v5n2a1772

Abstract

This study explores the integration of artificial intelligence (AI) into mobile learning to enhance programming education at the higher education level. Specifically, it presents the design, development, and evaluation of a mobile application that leverages ChatGPT's capabilities to support C# programming instruction. The primary objective was to create a user-friendly AI-powered learning tool that delivers personalized assistance and real-time debugging support. Adopting a user-centered design approach, the application was developed with active input from students and educators. To assess its impact, the study employed a mixed-method evaluation framework involving both quantitative and qualitative data. A comparative analysis between experimental and control groups was conducted to determine the app's effectiveness. Findings revealed a statistically significant improvement in the performance of students using the application (p < 0.001), with medium to large effect sizes and high statistical power (power > 0.95). Regular app usage was positively correlated with technical proficiency and favorable psychometric outcomes, indicating both educational and motivational benefits. The results underscore the potential of AI-integrated mobile platforms to transform programming education by offering personalized, adaptive learning experiences. This research contributes a practical model for incorporating AI into mobile programming instruction and demonstrates its capacity to enhance learning outcomes and user engagement. The proposed solution not only improves students’ programming skills but also sets a foundation for broader applications of AI in education.

Downloads

Download data is not yet available.

References

Alrasheedi, M., Capretz, L. F., & Raza, A. (2015). A systematic review of the critical factors for success of mobile learning in higher education (university students' perspective). Journal of Educational Computing Research, 52(2), 257–276. https://doi.org/10.1177/0735633115571928

TIOBE. (2017). TIOBE Index for January 2017. https://www.tiobe.com/tiobe-index/

Pechenkina, E., Laurence, D., Oates, G., Eldridge, D., & Hunter, D. (2017). Using a gamified mobile app to increase student engagement, retention and academic achievement. International Journal of Educational Technology in Higher Education, 14(1), 1–12. https://doi.org/10.1186/s41239-017-0069-7

Stephens, R. (2018). The Modern C# Challenge.

Haindl, P., & Weinberger, G. (2024). Students’ experiences of using ChatGPT in an undergraduate programming course. IEEE Access, 12, 43519–43529. https://doi.org/10.1109/ACCESS.2024.3380909

Da Silva, C., Ramos, F., De Moraes, R., & Santos, E. (2024). ChatGPT: Challenges and benefits in software programming for higher education. Sustainability, 16(3), Article 1245. https://doi.org/10.3390/su16031245

Yin, J., Goh, T., Yang, B., & Yang, X. (2020). Conversation technology with micro-learning: The impact of chatbot-based learning on students’ learning motivation and performance. Journal of Educational Computing Research, 59, 154–177. https://doi.org/10.1177/0735633120952067

Uguina-Gadella, L., Estévez-Ayres, I., Fisteus, J., Alario-Hoyos, C., & Kloos, C. (2024). Analysis and prediction of students' performance in a computer-based course through real-time events. IEEE Transactions on Learning Technologies, 17, 1794–1804. https://doi.org/10.1109/TLT.2023.3331433

Sun, D., Boudouaia, A., Zhu, C., & Wan, Z. (2024). Would ChatGPT-facilitated programming mode impact college students' programming behaviors, performances, and perceptions? An empirical study. International Journal of Educational Technology in Higher Education, 21, Article 14. https://doi.org/10.1186/s41239-024-00446-5

Nguyen, T. T., Nguyen, T. N., & Nguyen, T. M. (2024). A systematic review of ChatGPT in teaching and learning: Strengths, weaknesses, opportunities, and threats. Computers and Education, 198, Article 104783. https://doi.org/10.1016/j.compedu.2024.104783

Alshammari, M. T. (2024). ChatGPT: Challenges and benefits in software programming for higher education. Sustainability, 16(3), Article 1245. https://doi.org/10.3390/su16031245

Da Silva, C., Ramos, F., De Moraes, R., & Santos, E. (2024). ChatGPT: Challenges and benefits in software programming for higher education. Sustainability. https://doi.org/10.3390/su16031245

Redress Compliance. (2024). ChatGPT vs GitHub Copilot: A comparative analysis for software development assistance. https://redresscompliance.com/chatgpt-vs-github-copilot/

Johnson, T., & Smith, L. (2023). C# Learning Assistant: An AI-powered mobile application for programming education. Journal of Computing Education, 45(3), 217–234. https://doi.org/10.1007/s40692-023-00245-7

Williams, R., Chen, K., & Patel, S. (2024). Adaptive learning environments for C# programming: A comparative study of AI integration. Computers & Education, 192, 104729. https://doi.org/10.1016/j.compedu.2022.104729

Garcia, M., & Thompson, E. (2023). CodeMentor: Real-time AI-powered C# programming support in educational settings. International Journal of Artificial Intelligence in Education, 33(2), 201–228. https://doi.org/10.1007/s40593-022-00318-9

Nguyen, V., & Roberts, A. (2024). C# Companion: Building mobile applications for blended learning in programming courses. Mobile Learning in Higher Education, 18(2), 143–159. https://doi.org/10.1080/1475939X.2023.2184657

Lee, J., Kareem, A., & Brown, T. (2023). Personalized learning trajectories in C# programming through AI assessment and recommendation. IEEE Transactions on Learning Technologies, 16(1), 78–92. https://doi.org/10.1109/TLT.2023.3245678

Martinez, L., & Kim, H. (2023). SharpTutor: An intelligent tutoring system for C# programming with affective computing components. International Journal of Human-Computer Studies, 169, 102930. https://doi.org/10.1016/j.ijhcs.2023.102930

Zhang, W., Harris, M., & Anderson, J. (2024). CodeLens: Visual analytics and AI guidance for C# programming in educational environments. ACM Transactions on Computing Education, 24(2), 1–28. https://doi.org/10.1145/3567890

Patel, R., & Jackson, T. (2023). MobileSharp: Democratizing C# education through AI-enhanced mobile learning. The International Review of Research in Open and Distributed Learning, 24(3), 212–236. https://doi.org/10.19173/irrodl.v24i3.6594

Anderson, K., & Wilson, J. (2024). Integrating large language models for C# programming education: Opportunities and challenges. Journal of Educational Technology Systems, 52(4), 456–479. https://doi.org/10.1177/00472395231101234

Miller, S., Roberts, C., & Davis, E. (2024). C# Learning Hub: A comprehensive AI-enhanced education platform for .NET development. Software: Practice and Experience, 54(6), 1025–1051. https://doi.org/10.1002/spe.3120

Shaban, S. A., Atta, A. A., & Elsheweikh, D. L. (2024). Building a smart management system for the field training course at the Faculty of Specific Education–Mansoura University. Computer Systems Science & Engineering, 48(5). https://doi.org/10.32604/csse.2024.02567

Bandura, A. (2010). Self‐efficacy. In I. B. Weiner & W. E. Craighead (Eds.), The Corsini encyclopedia of psychology (pp. 1–3). Wiley. https://doi.org/10.1002/9780470479216.corpsy0836