DOI QR코드

DOI QR Code

머신러닝을 활용한 MBTI 기반 학습유형설계

MBTI-Based Learning Types Design Using Machine Learning

  • 오수민 (서울여자대학교 데이터사이언스학과) ;
  • 손서영 (서울여자대학교 데이터사이언스학과) ;
  • 양혜성 (서울여자대학교 데이터사이언스학과) ;
  • 박민서 (서울여자대학교 데이터사이언스학과)
  • 투고 : 2022.09.28
  • 심사 : 2022.11.01
  • 발행 : 2022.11.30

초록

MBTI(Myer Briggs Type Indicator)는 사람들의 성향을 직관적으로 파악하고 분류하는데 효과적인 성격유형검사이다. 이에 따라 학습 영역에 MBTI를 적용하려는 시도가 활발히 이뤄지고 있으나, MBTI를 활용하여 새로운 학습유형을 만드는 연구는 부족한 실정이다. 따라서 본 논문은 학습에 영향을 미치는 요인들을 살펴보고, 이를 특성으로 하는 머신러닝 알고리즘에 적용하여 새로운 학습 유형 MY, STI(MY, Study Type Indicator)를 구현했다. 데이터는 일반인 144명에게 구글폼으로 제작한 학습유형 검사를 실시하여 수집하였고, 머신러닝 중 지도 학습을 사용하여 학습시켰다. 그 결과 MY, STI의 정확도는 학습 방법, 학습 동기, 외부 자극 유무, 학습 시간 기준별 각각 0.933, 0.866, 0.844, 0.733으로 나타났다.

MBTI(Myer Briggs Type Indicator) is an effective personality type test to intuitively identify and classify people's tendencies. Accordingly, there are active attempts to apply MBTI to the learning area, but research on creating new learning types using MBTI is insufficient. Therefore, this paper examines the factors that affect learning and implements new learning types MY,STI(MY, Study Type Indicator) by applying them to a machine learning algorithm that has these characteristics. Data were collected by conducting a learning type test made with Google Forms on 144 general people, and supervised learning was used during machine learning. As a result, the accuracies of MY,STI were 0.933, 0.866, 0.844, and 0.733 for each learning method, learning motivation, presence or absence of external stimulus, and learning time criteria, respectively.

키워드

참고문헌

  1. R. M. Smith, "Learning how to learn : Applied Theory for Adults", Englewood Cliffs, NJ: Prenyice Hall, 1982.
  2. Eungyeong Han, Jaecheol Kim, "Relationship among the MBTI Personality Types and Academic Achievements according to Gender of University Students", JOURNAL OF EDUCATIONAL RESEARCH,14(2),149-172, 2007.
  3. Eun Jung Hur, Jae-Duck Lee, "The Effects of Learning Type on High School Students' Academic Achievement and Academic Self-concept", Korean Education Inquiry, 32(4), 121-139, 2014.
  4. Daewon Ko, "Research on learners' perception of environmental white noise as a factor of learning environment", Master's Thesis in Korea, Graduate School of Seoul National University, 2015.
  5. Nardi, Dario, "Neuroscience of Personality: Principles of the Psyche as a Living System" (2012). Systems Science Friday Noon Seminar Series. 48.
  6. Jung Rye Park, Sang Hoon Han. "The Effect of Goal Orientation, Motivation and Self-Concept on Learning Flow in Adult Learners". CNU journal of educational studies, vol. 34, pp.151-178, 2013. https://doi.org/10.18612/cnujes.2013.34.2.151
  7. Bora Lee, "The Influences of Learning Motivation, Self-Regulated Learning and Parental Learning Involvement upon Academic Achievement", Graduate School of Education, Founding University, 2012.
  8. Cox, D.R., Snell, E.J., Analysis of Binary Data, 2nd ed, New York, U.S.A: Routledge, 1970.
  9. SooYoung Kim. "Prediction of Hotel Bankruptcy Using Multivariate Discriminant Analysis, Logistic Regression and Artificial Neural Network", Journal of Tourism Sciences, vol. 30, no. 2, pp. 53-75, 2006.
  10. P. H. Swain and H. Hauska, "The decision tree classifier: Design and potential," in IEEE Transactions on Geoscience Electronics, vol. 15, no. 3, pp. 142-147, July 1977, DOI: 10.1109/TGE.1977.6498972.
  11. Jonghoo Choi, Doosung Seo. "Decision Trees and Its Applications", Journal of The Korean Official Statistics, vo1. 4, no. 1, pp.61-83, March 1999.
  12. Breiman, Leo., "Random forests", Machine Learning, Vol. 45, No. 1, pp. 5-32, 2001, DOI: https://doi.org/10.1023/A:1010933404324
  13. Younhak Oh, Han Kim, Jaesub Yun, Jong-Seok Lee."Using Data Mining Techniques to Predict Win-Loss in Korean Professional Baseball Games", Journal of the Korean Institute of Industrial Engineers, vol. 40, no. 1, pp.8-17, 2014. DOI: http://dx.doi.org/10.7232/JKIIE.2014.40.1.008