DOI QR코드

DOI QR Code

자동 분류 기술을 활용한 온라인 강의 평가 방법

Online Course Evaluation Method by Using Automatic Classification Technology

  • 이용배 (전주교육대학교 컴퓨터교육과)
  • Lee, Yong-Bae (Dept. of Computer Education, Jeonju National University of Education)
  • 투고 : 2020.06.19
  • 심사 : 2020.07.13
  • 발행 : 2020.08.31

초록

국내외 온라인 강의에 대한 학습자와 프로그램 수요는 증가하고 있지만 이에 대한 평가 방법은 설문지에 의한 정량적인 수치에 의존하고 있으며 객관적인 학습 만족도에 대한 평가 방법은 마련돼 있지 않다는 것이 문제점으로 드러나고 있다. 본 연구에서는 온라인 학습 시스템의 게시판에 있는 빅 데이터 메시지를 분석하여 온라인 강의를 평가하는 방법을 제안하려고 한다. 실제로 빅 데이터 분석기법 중 중요한 기술로 인식되는 자동분류 기법을 적용하여 온라인 강의 평가에 시범 적용해 보았으며 델파이 분석 결과에서도 평가 항목과 분류 결과 등이 온라인 강의 평가에 적합하고 학교나 기관에서 적용해볼 만하다는 결론을 얻었다. 본 연구는 빠르게 축적되고 있는 빅 데이터 분석기술을 가장 변화가 늦은 교육 분야에 적용해 보고 확장 가능성을 진단해보는데 의의가 있다.

Although the need for international online courses and the number of online learners has been rapidly increasing, the online class evaluation has been mostly relying on the quantitative survey analysis. So a more objective evaluation method has to be developed to more accurately assess online course satisfaction. This study highlights the benefits of using big data analysis from the bulletin board messages of online learning system as a method to evaluate the online courses. In fact, automatic classification technology is recognized as an important technology among big data analysis techniques. Our team applied this technique to evaluate the online courses. From the delphi analysis results, suggested method was concluded that the evaluation items and classification results are suitable for online course evaluation and applicable in schools or institutions. This study has confirmed that the rapidly accumulating big data analysis technology can be successfully applied to the education sector with the least change. It also diagnosed a meaningful possibility to expand the big data analysis for further application.

키워드

참고문헌

  1. Alastair Blyth, Julie Velissaratou(2020), How do we re-open schools after the coronavirus pandemic?, OECD Education and Skills Today.
  2. EBS(2018), Performance Analysis and Improvement Plan Research EBS SAT Lecture Business, EBS research.
  3. Hye Sook Kim, Ahn Na Shin, Han Sung Kim(2020), Education Informatization Level and Implications of Korea through OECD PISA 2018, KERIS Issue report, RM 2020-7.
  4. Hyung Nam Moon, Yong Ki Lee(2001), E-business Success Strategy through Website Evaluation, Hankyoungsa Press.
  5. Jae Yoon Noh(2020), A Study On Efficient Learner Level Classification Based on Machine Learning, Graduate School Sejong University.
  6. KERIS(2006), E-learning quality management guidelines for the operation of the national e-learning quality control center, KERIS research, RR 2006-1.
  7. Keun Ho Choi, Gun Woo Kim(2018), Building Battery Deterioration Prediction Model using Real Field Data, Journal of Intelligence and Information Systems, 24(2), 243-264. https://doi.org/10.13088/JIIS.2018.24.2.243
  8. Kyung Rog Kim, Hye Jin Song, Nam Mee Moon(2017), Topic Modeling for Automatic Classification of Learner Question and Answer in Teaching-Learning Support System, JDCS, 18(2), 339-346.
  9. Ministry of Education(2019), 2019 Statistics of Lifelong Education, SM2019-10.
  10. Ministry of Education(2019), Result Announcement of OECD PISA 2018, Ministry Press Release
  11. OECD(2019), Korea - Country Note - PISA 2018 Results, OECD 2019 Volumes I-III.
  12. Sang Chul Choi(2018), Inferring Transmission Routes of Avian Influenza during the H5N8 Outbreak of South Korea in 2014 using Epidemiological and Genetic Data, Korean Journal of Microbiology, 54(3), 254-265. https://doi.org/10.7845/kjm.2018.8044
  13. Tae-eun Moon, Hyung Nam Moon(2008), A Study on the Website Evaluation and Improvement of Korean Cyber University Websites, Journal of Intelligence and Information Systems, 14(2), 137-156.
  14. Yong-Bae Lee, Sung Hyun Myaeng(2011), Analysis of Domain Adaptability of Genre-based Classification Models, Journal of KIISE, 38(8), 441-451.
  15. Yong-Bae Lee(2014), Classification Accuracy by Deviation-based Classification Method with the Number of Training Documents, Journal of digital convergence, 12(6), 325-332. https://doi.org/10.14400/JDC.2014.12.6.325