DOI QR코드

DOI QR Code

Validity Analysis of Python Automatic Scoring Exercise-Problems using Machine Learning Models

머신러닝 모델을 이용한 파이썬 자동채점 연습문제의 타당성 분석

  • Kyeong Hur (Department of Computer Education, Gyeong-In National University of Education)
  • 허경 (경인교육대학교 컴퓨터교육과)
  • Received : 2023.04.01
  • Accepted : 2023.04.15
  • Published : 2023.04.30

Abstract

This paper analyzed the validity of exercise problems for each unit in Python programming education. Practice questions presented for each unit are presented through an online learning system, and each student uploads an answer code and is automatically graded. Data such as students' mid-term exam scores, final exam scores, and practice questions scores for each unit are collected through Python lecture that lasts for one semester. Through the collected data, it is possible to improve the exercise problems for each unit by analyzing the validity of the automatic scoring exercise problems. In this paper, Orange machine learning tool was used to analyze the validity of automatic scoring exercises. The data collected in the Python subject are analyzed and compared comprehensively by total, top, and bottom groups. From the prediction accuracy of the machine learning model that predicts the student's final grade from the Python unit-by-unit practice problem scores, the validity of the automatic scoring exercises for each unit was analyzed.

본 논문은 파이썬 프로그래밍 교육에서 단원별 연습문제의 타당성을 분석하였다. 단원별로 제시되는 연습문제는 온라인 학습 시스템을 통해 제시되고 학생 각자가 답안 코드를 업로드하여 자동으로 채점된다. 한학기 동안 진행되는 파이썬 교육을 통해, 학생들의 중간시험점수, 기말시험 점수 그리고 각 단원별 연습문제 점수 등 데이터가 수집된다. 수집된 데이터들을 통해, 자동채점 연습문제들의 타당도를 분석하여 단원별 연습문제들을 개선할 수 있다. 본 논문에서는 자동 채점 연습문제들의 타당도를 분석하기 위해, Orange 머신러닝 도구를 사용하였다. 파이썬 과목에서 수집된 데이터를 전체, 상위권 그리고 하위권 그룹별로 4가지 분석을 실시하고 종합적으로 비교한다. 파이썬 단원별 연습문제 점수들로부터 학생의 최종 성적을 예측하는 머신러닝 모델의 예측 정확도로부터 단원별 자동채점 연습문제의 출제 타당도를 분석하였다.

Keywords

References

  1. J. K. Jeong, "Design and construct of programming assessment system based on online judge for a science high school student," Korea National University of Education, 2010. 
  2. Codle, Team Monolith, 2022, [Online]. Available: https://codle.io/. 
  3. W. Y. Chang and S. S. Kim, "Development and application of algorithm judging system : analysis of effects on programming learning," The Journal of Korean Association of Computer Education, vol. 17, no. 4, pp. 45-57, 2014.  https://doi.org/10.32431/KACE.2014.17.4.005
  4. Orange, University of Ljubljana, 2023, [Online]. Available: https://orangedatamining.com/. 
  5. S. S. Kim, S. H. Oh, and S. S. Jeong, "Development and application of problem bank of problem solving programming using online judge system in data structure education," The Journal of Korean Association of Computer Education, vol. 21, no. 4, pp. 11-20, 2018.  https://doi.org/10.32431/kace.2018.21.5.002
  6. S. S. Jeong, "The effects of programming education using an automatic programming assessment system on learning flow of general high school students," Korea National University of Education, 2019. 
  7. W. Y. Chang, "The effects of online judge system in programming education on learning motivation and thinking : structural relationships between factors," Korea National University of Education, 2020. 
  8. K. Hur, "Python basic programming curriculum for non-majors and development analysis of evaluation problems," Journal of Practical Engineering Education, vol. 14, no. 1, pp. 75-83, 2022. https://doi.org/10.14702/JPEE.2022.075