Authors
- Patarakin Yevgeny D. Doctor of Education Sciences, Associate Professor
- Burov Vasiliy V.
- Salimullin Karim D.
- Soshnikov Dmitry V. PhD in Physics and Mathematics
Annotation
This study explores the potential of modern generative models for automatically generating educational task texts. Building on prior research in educational task
generation, we focused on leveraging generative artificial intelligence to create tasks based on textbook content, leading to the development of a multiple-choice educational task generator. This tool, powered by a large language model, empowers educators to independently craft tasks for their courses. In the experiments, teachers from various disciplines were involved in selecting topics for the generation of educational materials. The results demonstrate the capability of modern large language models to generate simple text-based multiple-choice questions suitable for use. While the current need for manual verification and refinement of distractors by educators presents a challenge, it is anticipated that generative AI will address this soon. The study sheds light on the potential of generative AI in education.
How to link insert
Patarakin, Y. D., Burov, V. V., Salimullin, K. D. & Soshnikov, D. V. (2024). EXPERIMENTAL USE OF EDUCATIONAL MATERIALS DEVELOPED USING ARTIFICIAL INTELLIGENCE IN NATURAL SCIENCE EDUCATION Bulletin of the Moscow City Pedagogical University. Series "Pedagogy and Psychology", 18 (1-1), 78. https://doi.org/10.25688/2076-9121.2024.18.1-1.04
References
1.
1. Kurdi, G., Parsia, B., Leo, J., & Sattler, U. (2020). A Systematic Review of Automatic Question Generation for Educational Purposes. Int J Artif Intell Educ, 30(1),
121–204.
2.
2. Ch, D. R., & Saha, S. K. (2020). Automatic Multiple Choice Question Generation From Text: A Survey. IEEE Transactions on Learning Technologies, 13(1), 14–25.
3.
3. Matos, R. M. F. de. (2022). Automatic Generation of Multiple Choice Questions. Dissertation in the context of the Master in Informatics Engineering, specialization in Intelligent Systems, advised by Prof. Hugo Oliveira and Hugo Amaro and presented to the Department of Informatics Engineering of the Faculty of Sciences and Technology of the University of Coimbra.
4.
4. Moore, S., Nguyen, H. A., Fang, E., & Stamper, J. (2023). Crowdsourcing the evaluation of multiple-choice questions using item-writing flaws and bloom’s taxonomy. In: arXiv:2205.01730v1 [cs.CL].
5.
5. Hadifar, A., Bitew, S. K., Deleu, J., Develder, C., & Demeester, T. (2023). EduQG: A multi-format multiple-choice dataset for the educational domain. IEEE Access, 11, 20885–20896.
6.
6. Laban, P., Wu, Ch.-Sh., Murakhovska, L., Liu, W., & Xiong, C. (2022). Quiz Design Task: Helping Teachers Create Quizzes with Automated Question Generation. In: Findings of the Association for Computational Linguistics: NAACL 2022, July 10–15, 2022 (pp. 102–111). Association for Computational Linguistics.
7.
7. Patarakin, E. D., Burov, V., & Sochnikov, D. (2023). Experimental generation of educational tasks in natural science disciplines using artificial intelligence. MCU Journal of Pedagogy and Psychology, 17(4), 38–58.
8.
8. Vachkova, S. N., Patarakin, E. D., & Petryaeva, E. Y. (2020). Content Quality of Lesson Scenarios in Moscow E-School. SHS Web Conf, 79, 01017.
9.
9. Parandekar, S., Patarakin, E., & Yayla, G. (2023). A Modern Aspect of Instrumental Literacy: Coding. In: Dobryakova, M., Froumin, I., Barannikov, K., Moss, G., Remorenko, I., & Hautamäki, J. (Eds.). Key Competences and New Literacies: From Slogans to School Reality (pp. 367–390). UNIPA Springer Series. Springer, Cham.