You are here: Home / Vol. 17, issue 1 / Paper 2026-29

Paper 2026-29

ПРОЕКТИРАНЕ НА ПЕДАГОГИЧЕСКИ СИТУАЦИИ ЗА ДЕТСКАТА ГРАДИНА С ГЕНЕРАТИВЕН ИЗКУСТВЕН ИНТЕЛЕКТ – СРАВНИТЕЛЕН АНАЛИЗ НА CHATGPT И GEMINI

Надежда Ангелова Калоянова
Бургаски държавен университет „Проф. д-р Асен Златаров“, Бургас

DESIGNING PEDAGOGICAL SITUATIONS FOR KINDERGARTEN WITH GENERATIVE ARTIFICIAL INTELLIGENCE – COMPARATIVE ANALYSIS OF CHATGPT AND GEMINI

Nadezhda Angelova Kaloyanova
Burgas State University „Prof. Dr Asen Zlatarov”, Burgas

Abstract: The article presents the capabilities of two generative language models – ChatGPT and Gemini – to assist the preschool teacher in designing pedagogical situations for the fourth age group in kindergarten. The aim is to track the change in the generated pedagogical product with successive complication and structuring of the text requests and to compare the capabilities of the two models for compliance with pre-set educational parameters such as: specific educational goals, age characteristics, organizational conditions, methodological approaches, aspects of inclusion of children from specific groups and assessment criteria. A comparative study was conducted, in which an identical sequence of general, contextualized and corrective prompts was addressed to both tools. The resulting pedagogical situations are assessed through a system of criteria for compliance with the educational program, pedagogical expediency, age adequacy, children’s activity, applicability, inclusive potential and opportunities for assessing the expected results. Based on the comparative analysis, a methodological model for pedagogically guided co-design between the teacher and generative artificial intelligence is proposed.

Keywords: generative language models (generative AI), pedagogical design; pedagogical situation; preschool education; structured pedagogical prompt

References:

  1. Kibar, P.N., Ilgaz, H. (2026). The intersection of artificial intelligence and instructional design practice: a systematic review. Education Tech Research Dev (2026). https://doi.org/10.1007/s11423-026-10624-z
  2. Moundridou, M., Matzakos, N., & Doukakis, S. (2024). Generative AI tools as educators’ assistants: Designing and implementing inquiry-based lesson plans. Computers and Education: Artificial Intelligence, 7, Article 100277. https://doi.org/10.1016/j.caeai.2024.100277
  3. Wang, Z., Liu, M., & Islam, A. Y. M. A. (2026). Reimagining teacher – AI co-design in learning task design: Trends and perspectives. Humanities and Social Sciences Communications, 13, 757.
  4. Wang, Q., Li, Q., Cui, X., Xu, Y., Wang, N., & Wang, M. (2025). Integrating AI in preschool teacher education: The mediating role of self-efficacy in health education and the moderating effect of technological proficiency. Journal of Baltic Science Education, 24(4), 721–741. https://doi.org/10.33225/jbse/25.24.721
  5. Kölemen, E.B., Yıldırım, B. (2025). A new era in early childhood education (ECE): Teachers’ opinions on the application of artificial intelligence. Educ Inf Technol 30, 17405–17446 https://doi.org/10.1007/s10639-025-13478-9
  6. Li, Y. (2023). A practical survey on zero-shot prompt design for in-context learning. Proceedings of RANLP 2023, 641 – 650.
  7. Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023). Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. ACM Computing Surveys, 55(9), 1 – 35. https://doi.org/10.1145/3560815
  8. Wei, J., Wang, X., Schuurmans, D., et al. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35, 24824 – 24837.
  9. Kojima, T., Gu, S. S., Reid, M., Matsuo, Y., & Iwasawa, Y. (2022). Large language models are zero-shot reasoners. Advances in Neural Information Processing Systems, 35, 22199 – 22213
  10. Yao, S., Yu, D., Zhao, J., et al. (2023). Tree of thoughts: Deliberate problem solving with large language models. Advances in Neural Information Processing Systems, 36.)
  11. Wang, X., Wei, J., Schuurmans, D., et al. (2023). Self-consistency improves chain of thought reasoning in language models. Proceedings of ICLR 2023, https://webdocs.cs.ualberta.ca/~dale/papers/iclr23b.pdf
  12. Yao, S., Zhao, J., Yu, D., et al. (2023). ReAct: Synergizing reasoning and acting in language models. Proceedings of ICLR 2023. https://openreview.net/pdf?id=WE_vluYUL-X
  13. Kong, A., Zhao, S., Chen, H., et al. (2024). Better zero-shot reasoning with role-play prompting. Proceedings of NAACL 2024 – Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 4099 – 4113, Mexico City, Mexico. Association for Computational Linguistics DOI: https://doi.org/10.48448/zprd-1b16
  14. Dornburg, A., & Davin, K.J. (2024). To what extent is ChatGPT useful for language teacher lesson plan creation? ArXiv, abs/2407.09974. https://doi.org/10.48550/arXiv.2407.09974

(Endnotes:)

1. Uchtivoto obrashtenie e zapazeno, makar che po sashtestvo e izlishno, tay kato otrazyava profesionalen i visok stil na obshtuvane, koyto ne biva da se gubi – belezhka na avtora

READ FULL PAPER