한국수학교육학회지시리즈E:수학교육논문집 (Communications of Mathematical Education)

  • 제38권1호
  • /
  • Pages.49-67
  • /
  • 2024
  • /
  • 1226-6663(pISSN)
  • /
  • 2287-9935(eISSN)
한국수학교육학회 (Korean Society of Mathematical Education)
권호 표지
DOI QR코드

DOI QR Code

수학 문장제 해결과 관련한 ChatGPT의 교수학적 활용 방안 모색

A study on the didactical application of ChatGPT for mathematical word problem solving

  • 투고 : 2024.02.05
  • 심사 : 2024.03.11
  • 발행 : 2024.03.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

최근 인공지능 언어 모델의 다양한 활용에 대한 관심이 높아지면서 수학교육에서의 교수학적 활용 방안 모색에 대한 필요성이 강조되고 있다. 인공지능 언어 모델은 자연어 처리가 가능하다는 특징으로 인하여 수학 문장제 해결과 관련된 활용이 기대된다. 인공지능 언어 모델 중 하나인 ChatGPT의 성능을 확인하기 위하여 초등학교 교과서에 제시된 문장제를 해결하도록 지시하였으며 풀이 과정 및 오류를 분석하였다. 분석 결과, 인공지능 언어 모델은 81.08%의 정답률을 나타내었으며 문제 이해 오류, 식 수립 오류, 계산 오류 등이 발생하였다. 이러한 문장제 해결 과정 및 오류 유형의 분석을 바탕으로 인공지능 언어 모델의 교수학적 활용 방안과 관련된 시사점을 제안하였다.

Recent interest in the diverse applications of artificial intelligence (AI) language models has highlighted the need to explore didactical uses in mathematics education. AI language models, capable of natural language processing, show promise in solving mathematical word problems. This study tested the capability of ChatGPT, an AI language model, to solve word problems from elementary school textbooks, and analyzed both the solutions and errors made. The results showed that the AI language model achieved an accuracy rate of 81.08%, with errors in problem comprehension, equation formulation, and calculation. Based on this analysis of solution processes and error types, the study suggests implications for the didactical application of AI language models in education.

키워드

참고문헌

  1. Kang, W., Baek, S., Jeon, I., Lee, K., Kim, Y., ..., Lee, M. (2023). Mathematics 6-2. Daekyo.
  2. Kang, Y.(2023) Exploring the use of AI language models in terms of pedagogical practice and research in mathematics education. Journal of Educational Research in Mathematics, 33(4), 1023-1040.
  3. Ministry of Education (2020a). Mathematics 6-1. Visang.
  4. Ministry of Education (2020b). Mathematics 6-2. Visang.
  5. Kwon, O., Oh, S., Yoon, J., Lee, K., Shin, B., & Jung, W.(2023). Analyzing mathematical performances of chatGPT: Focusing on the solution of national assessment of educational achievement and the college scholastic ability test. Communication of Mathematical Education, 37(2), 233-256. https://doi.org/10.7468/JKSMEE.2023.37.2.233
  6. Park, K., Chong, Y., Ko, J., Kwon, S., Nam, J., ..., Prak, J. (2023). Mathematics 6-2. Bookdonga.
  7. Park, M., Kang, K., Kim, D., Lim, D., Kim, S., ..., Kim E. (2023). Mathematics 6-2. Chunjae.
  8. Park, S., Ryu, S., Kim, S., Kwon, S., Kim, N., ..., Kang, H. (2023a). Mathematics 6-1. YBM.
  9. Park, S., Ryu, S., Kim, S., Kwon, S., Kim, N., ..., Kang, H. (2023b) Mathematics 6-2. YBM.
  10. Park, J., Ryu, S. & Lee, J.(2012). The analysis of mathematics error type that appears from the process of solving problem related to real life. Journal of the Korean School Mathematics Society, 15(4), 699-718.
  11. Son, T. (2023). Exploring the possibility of using ChatGPT in mathematics education: Focusing on student product and pre-service teachers' discourse related fraction problems. Education of Primary School Mathematics, 26(2), 99-113. https://doi.org/10.7468/JKSMEC.2023.26.2.99
  12. Seok, k. & Paik, S.(2004). An analysis of errors on the process of word problem solving in the elementary mathematics. Journal of Elementary Mathematics Education in Korea, 8(2), 147-168.
  13. Ahn, B., Na, G., Kim, M., Lee, K., Ryu, H., ..., Choi, J. (2023). Mathematics 6-2. Bookdonga.
  14. Lee, B. O., & Ahn, B. G. (2008). An analysis on sentence structures and interpretation errors in word problems in mathematics-focussing on the 2nd grade elementary students. Journal of Elementary Mathematics Education in Korea, 12(2), 185-204.
  15. Chang, H., Seo, D., Kim, M., Kim, S., Kim, J., ..., Kim, C. (2023). Mathematics 6-2. Mirae-n.
  16. Han, D., Ko, E., Lee, S., Cho, H., Han, S., ..., Shin, H. (2023a). Mathematics 6-1. Chunjae.
  17. Han, D., Ko, E., Lee, S., Cho, H., Han, S., ..., Shin, H. (2023b). Mathematics 6-2. Chunjae.
  18. Azaria, A. (2022). ChatGPT usage and limitations. HAL Open Science. hal-03913837
  19. Davis, E. (2023). Mathematics, word problems, common sense, and artificial intelligence. arXiv preprint arXiv:2301.09723.
  20. OpenAI (2023a). Improving mathematical reasoning with process supervision. https://openai.com/research/improving-mathematical-reasoning-with-process-supervision
  21. Remoto, J. P. (2023). ChatGPT and other AIs: Personal relief and limitations among mathematics-oriented learners. Environment and Social Psychology, 9(1). 1-13. https://doi.org/10.54517/esp.v9i1.1911
  22. Verschaffel, L., Schukajlow, S., Star, J., & Van Dooren, W. (2020). Word problems in mathematics education: A survey. ZDM, 52, 1-16.
  23. Zong, M., & Krishnamachari, B. (2023, June). Solving math word problems concerning systems of equations with gpt-3. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 37, No. 13, pp. 15972-15979).