IMPLEMENTATION OF DIGITAL TWINS BASED ON GPT-3.5 FOR ENHANCING ENGLISH LANGUAGE LEARNING IN HIGHER EDUCATION INSTITUTIONS

Authors

  • V. Didok Харківський національний університет міського господарства імені О.М. Бекетова
  • M. Pan Харківський національний університет міського господарства імені О.М. Бекетова

DOI:

https://doi.org/10.33042/2522-1809-2024-6-187-8-11

Keywords:

digital twins, artificial intelligence, GPT-3.5, interactive learning, personalized learning, natural language processing

Abstract

This paper presents the development of an interactive web-based platform aimed at enhancing English language learning through the utilization of digital twins, powered by the GPT-3.5 model. The platform integrates three primary services essential for language learning: vocabulary acquisition, grammar checking, and conversational practice via simulated interlocutors, offering a dynamic, personalized learning experience. Detailed technical aspects of the system’s architecture are discussed, highlighting the implementation of the Model-View-Controller (MVC) framework, which ensures modularity and scalability. The platform’s backend is developed using C# for reliability and performance, while the frontend leverages HTML, CSS, JavaScript, and the Bootstrap framework to create a responsive, user-friendly interface that adapts to various screen sizes and devices.
To support large volumes of user data, a Microsoft Azure SQL Database is employed for robust data management, enabling efficient storage and retrieval of user information, interaction histories, and progress logs. Integration with GPT-3.5 via OpenAI's API facilitates real-time query processing and response generation, making the platform a powerful tool.
The platform uses advanced personalization algorithms to adjust learning content based on user preferences, progress, and interaction history. This personalized approach increases student engagement and promotes more effective learning outcomes by adapting content to individual needs.
Security and ethical considerations are addressed through encryption protocols and authentication mechanisms. In addition, OpenAI’s built-in content filtering systems ensure that inappropriate or harmful content is blocked, safeguarding users while maintaining high ethical standards. Furthermore, a detailed cost calculation model for token usage is presented, which allows for precise tracking of operational costs, ensuring the platform’s long-term sustainability.
By integrating cutting-edge technology with pedagogical principles, this platform demonstrates the potential to revolutionize English language learning in higher education institutions, making it more interactive, personalized, and effective.

Author Biographies

V. Didok, Харківський національний університет міського господарства імені О.М. Бекетова

здобувач вищої освіти 2-го курсу магістратури навчально-наукового інституту енергетичної, інформаційної та транспортної інфраструктури

M. Pan, Харківський національний університет міського господарства імені О.М. Бекетова

кандидат технічних наук, доцент кафедри комп’ютерних наук та інформаційних технологій

References

Marron, L. (2023). Exploring the Potential of ChatGPT 3.5 in Higher Education: Benefits, Limitations, and Academic Integrity. In Handbook of Research on Redesigning Teaching,Learning, and Assessment in the Digital Era (pp. 1-24). DOI: 10.4018/978-1-6684-8292-6.ch017. Retrieved from https://www.igi-global.com/chapter/exploring-the-potential-of-chatgpt-35-in-higher-education/323557

Stojanov, A. (2023). Learning with ChatGPT 3.5 as a more knowledgeable other: an autoethnographic study. International Journal of Educational Technology in Higher Education, 20, Article 35. DOI: 10.1186/s41239-023-00404-7. Retrieved from https://educationaltechnologyjournal.springeropen.com/articles/10.1186/s41239-023-00404-7

Dempere, J., Modugu, K., Allam, H., & Ramasamy, L. K. (2023). The impact of ChatGPT on higher education. Frontiers in Education, 8. DOI: 10.3389/feduc.2023.1206936. Retrieved from https://www.frontiersin.org/articles/10.3389/feduc.2023.1206936/full.

OpenAI. (2023). GPT-3.5 Language Model Documentation. Retrieved from https://platform.openai.com/docs/models/gpt-3-5

Microsoft. (2023). ASP.NET Core MVC Documentation. Retrieved from https://learn.microsoft.com/en-us/aspnet/core/mvc/

OpenAI. (2023). OpenAI API Documentation. Retrieved from https://platform.openai.com/docs

Krasner, G. E., & Pope, S. T. (1988). A cookbook for using the model-view-controller user interface paradigm in Smalltalk-80. Journal of Object-Oriented Programming, 1(3), 26-49.

Bootstrap. (2023). Bootstrap 5 Documentation. Retrieved from https://getbootstrap.com/docs/

Mozilla Developer Network. (2023). JavaScript Documentation.Retrieved from https://developer.mozilla.org/en-US/docs/Web/JavaScript

Mozilla Developer Network. (2023). CSS Documentation. Retrieved from https://developer.mozilla.org/en-US/docs/Web/CSS

Published

2024-12-17

How to Cite

Didok, V., & Pan, M. (2024). IMPLEMENTATION OF DIGITAL TWINS BASED ON GPT-3.5 FOR ENHANCING ENGLISH LANGUAGE LEARNING IN HIGHER EDUCATION INSTITUTIONS. Municipal Economy of Cities, 6(187), 8–11. https://doi.org/10.33042/2522-1809-2024-6-187-8-11

Issue

Section

статьи