EĞİTİMDE ÖLÇMEDE YAPAY ZEKANIN ENTEGRASYONU: MADDE TEPKİ KURAMI KAPSAMINDA VERİ ÜRETİMİNDE CHATGPT'NİN ETKİLİLİĞİ

Abstract

Bu çalışmanın amacı, Madde Tepki Kuramı (MTK) kapsamında R programlama diliyle gerçekleştirilen veri üretimine yönelik algoritmaların geliştirilmesinde ChatGPT 3.5’nin etkililiğini araştırmaktır. Bu kapsamda, ChatGPT 3.5 ve araştırmacılar tarafından yazılan algoritmalarla, İki Parametreli Lojistik Modele (2PLM) göre üretilen veri setleri üzerinde geçerlik incelemeleri yapılmıştır. Yapılan incelemelerde, veri setlerinin MTK varsayımlarını ve madde parametrelerinin simülasyon koşullarını karşılama durumları dikkate alınmıştır. Sonuç olarak ChatGPT 3.5 algoritmalarının, MTK varsayımlarına uygun veri üretimi konusunda oldukça başarılı olduğu, ancak madde parametrelerinin simülasyon koşullarını karşılama hususunda, araştırmacılar tarafından geliştirilen algoritmaya kıyasla daha az etkili olduğu belirlenmiştir. Bu kapsamda ChatGPT 3.5, MTK’ya yönelik veri üretimi algoritmalarının geliştirilmesinde, araştırmacılara destek verebilecek faydalı bir araç olarak önerilmektedir.

Keywords

• ChatGPT
• Madde Tepki Kuramı
• veri üretimi
• simulasyon
• R programlama dili

INTEGRATION OF ARTIFICIAL INTELLIGENCE IN EDUCATIONAL MEASUREMENT: EFFICACY OF CHATGPT IN DATA GENERATION WITHIN THE SCOPE OF ITEM RESPONSE THEORY

Abstract

The aim of this study is to investigate the effectiveness of ChatGPT 3.5 in developing algorithms for data generation within the framework of Item Response Theory (IRT) using the R programming language. In this context, validity examinations were conducted on data sets generated according to the Two-Parameter Logistic Model (2PLM) with algorithms written by ChatGPT 3.5 and researchers. These examinations considered whether the data sets met the IRT assumptions and the simulation conditions of the item parameters. As a result, it was determined that while ChatGPT 3.5 was quite successful in generating data that met the IRT assumptions, it was less effective in meeting the simulation conditions of the item parameters compared to the algorithm developed by the researchers. In this regard, ChatGPT 3.5 is recommended as a useful tool that researchers can use in developing data generation algorithms for IRT.

Keywords

• ChatGPT
• Item Response Theory
• data generation
• simulation
• R programming language

References

1. Horn, J. L. (1965). A rationale and test for the number of factors in factor analysis. Psychometrika, 30, 179-185.
2. Hu, K. (2023) ChatGPT sets record for fastest-growing user base - analyst note,February 2, 〈https://www.reuters.com/technology/chatgpt-sets-record-fastest-growing-userbase-analyst-note-2023–02-01/>
3. Huang, R. (2019). Educational technology a primer for the 21st century. Springer Nature Singapore Pte Ltd.
4. Jaber, M. A., Beganovic, A., & Abd Almisreb, A. (2023). Methods and Applications of ChatGPT in Software Development: A Literature Review. Southeast Europe Journal of Soft Computing, 12(1), 08-12.http://dx.doi.org/10.21533/scjournal.v12i1.251
5. Kashefi, A., & Mukerji, T. (2023). Chatgpt for programming numerical methods. Apr. 2023, arXiv:2303.12093.
6. Khoury, R., Avila, A. R., Brunelle, J. and Camara, B. M. (2023) “How Secure is Code Generated by ChatGPT?” Apr. 2023, arXiv:2304.09655.
7. King, M. R. (2023). Outsourcing Your Faculty Application to ChatGPT: Would this Work? Should this Work?. Cellular and Molecular Bioengineering, 16(4), 423-426. https://doi.org/10.1007/s12195-023-00777-9
8. Kundalia, N.D. (2023). ChatGPT and the future of writing. Hindustan Times. Retrieved January 31, 2023, from 〈https://www.hindustantimes.com/books/ chatgpt-and-the-future-of-writing-101675090609362.html〉

9. Laumer, S., Maier, C., Eckhardt, A., & Weitzel, T. (2016). Work routines as an object of resistance during information systems implementations: Theoretical foundation and empirical evidence. European Journal of Information Systems, 25(4), 317–343. https://doi.org/10.1057/ejis.2016.1