Journal of The Korean Association of Information Education (정보교육학회논문지)

Korea Association of Information Education (한국정보교육학회)
권호 표지
DOI QR코드

DOI QR Code

Analysis of Educational Issues through Topic Modeling of National Petitions Text

국민청원글의 토픽 모델링을 통한 교육이슈 분석

  • 심재권 (고려대학교 영재교육원)
  • Received : 2021.07.03
  • Accepted : 2021.07.14
  • Published : 2021.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

Education related issues are social problems in which various groups and situations are intricately linked to each other. It is difficult to find issues by analyzing social phenomena related to education. Korean based text analysis can be analyzed in a quantitative. With the development of text analysis techniques, research results have been recently achieved, and it can be fully utilized to derive educational issues from text data in Korean. In this study, petition articles in the field of childcare/education were collected on the online-board of the Blue House National Petition website, and text analysis was used to derive issues in the education world. The analysis derived 6 topics through Latent Dirichlet Allocation(LDA) among topic modeling techniques. The association rules of major keywords were analyzed and visualized as graphs. In addition to deriving educational issues through the existing questionnaire, it can provide implications for future research directions and policies in that issues can be sufficiently discovered through text-based analysis methods.

교육과 관련된 이슈는 다양한 집단과 상황이 서로 복잡하게 연계된 사회문제로 교육과 관련된 현상을 분석하여 이슈와 문제를 구체적으로 발견하는 것은 쉽지 않은 일이다. 한국어 기반 텍스트 분석은 정량적인 형태로 분석이 가능하고, 텍스트 분석기법의 발전에 따라 연구적인 성과를 내고 있어 교육과 관련된 이슈를 한국어 텍스트로 된 데이터에서 도출하는데 충분히 활용할 수 있다. 본 연구는 청와대 국민청원 홈페이지 게시판의 육아/교육 분야의 청원글을 수집하고 텍스트 분석방법을 활용하여 교육계의 이슈와 문제를 도출하고자 하였다. 분석은 토픽 모델링 기법 중 잠재 디리클레 할당(LDA)을 통해 6개 토픽을 도출하였고, 주요 키워드의 연관규칙을 분석하여 그래프로 시각화하였다. 기존의 설문을 통한 교육의 이슈를 도출하는 방법 이외에 추가로 텍스트 기반의 분석방법을 통해 이슈를 충분히 발견할 수 있다는 점에서 향후 연구의 방향과 정책에 시사점을 제공할 수 있다.

Keywords

References

  1. Blue House National Petition Homepage [Internet]. https://www1.president.go.kr/petitions/FAQ
  2. C. W. Woo and J. Y. Lee (2020). Investigation of Research Topic and Trends of National ICT Research-Development Using the LDA Model. Journal of the Korea Convergence Society, 11(7), 9-18. https://doi.org/10.15207/JKCS.2020.11.7.009
  3. C.D. Kang (2008). A Social Historical Study on the Korean Paranoid Educational Fervor and Status Desire. The Korea Educational Review, 14(2), 5-32.
  4. D. Newman, J. H. Lau, K. Grieser, and T.Baldwin (2010). Automatic Evaluation of Topic Coherence. Human Language Technologies. The 2010 Annual Conference of the North American Chapter of the ACL, 100-108.
  5. D.W. Yoon and H.J. Choe (2019). Analysis of the Core Concepts of Middle School Informatics Textbook Using Big Data Analysis Techniques. Journal of Creative Information Culture, 5(2), 157-164. https://doi.org/10.32823/jcic.5.2.201908.157
  6. David M. Blei, Andrew Y. Ng and Michael I. Jordanm (2003). Latent Dirichlet Allocation. Journal of Machine Learning Research, 3, 993-1022.
  7. J. W. Min, and J. K. Shim (2020). A Study on Analysis of National Petition Datafor Deriving Current Issues in Education. Journal of Creative Information Culture, 6(2), 57-64. https://doi.org/10.32823/JCIC.6.2.202008.57
  8. Jonathan Chang, Jordan Boyd-Graber, Sean Gerrish, Chong Wang and David M. Blei (2009). Reading Tea Leaves: How Humans Interpret Topic Models. Advances in Neural Information Processing Systems, 22, 288-296.
  9. M. Steyvers, and T. Griffiths (2007). Probabilistic topic models, Handbook of latent semantic analysis, Lawrence Erlbaum Associates Publishers.
  10. S. J. Kang and Y. J. Shon (2020). Phenomenon of Early Childhood Private Education through Topic Modeling Analysis: Focusing on Domestic Newspaper Articles and Blogs. Journal of Future Early Childhood Education, 27(1), 177-199. https://doi.org/10.22155/jfece.27.1.177.199
  11. S. Y. Kim (2020). Analysis of Research Trends in Journal of the Korean Society for Industrial and Applied Mathematics Using Topic Modeling and Implications for Industrial Mathematics Education. Secondary Education Research, 68(2), 267-293.
  12. T. K. Kim, H. R. Choi and H. C. Lee (2016). A Study on the Research Trends in Fintech using Topic Modeling. Journal of the Korea Academia-Industrial cooperation Society, 17(11), 670-681. https://doi.org/10.5762/KAIS.2016.17.11.670
  13. T. K. Son, and S. H, Hwang (2020). Analysis of the Research Trends of Domestic Elementary Mathematics Education Using Topic Modeling. Journal of Elementary Mathematics Education in Korea, 25(1), 61-80. https://doi.org/10.26844/ksepe.2020.25.4.61
  14. W.J. Choi, J.W. Seol, H.S. Jeong, and H.M. Yoon (2018). Comparison and Analysis of Subject Classification for Domestic Research Data. The Journal of the Korea Contents Association, 18(8), 178-186. https://doi.org/10.5392/JKCA.2018.18.08.178
  15. Y. Kim, N.K. Kim and S.J. Lee (2021). A Study on the Influence of Communication Characteristics of One-Person Media on Intention to Contents Acceptance: Focusing on the Mediating Effect of Parasocial Interaction. The Korean Journal of Advertising, 32(2), 163-188. https://doi.org/10.14377/KJA.2021.2.28.163
  16. Yon, B.N (2020). A Topic Modeling Analysis on the Policy Issues of Meister High School. Journal of Vocational Education & Training, 23(1), 39-67. https://doi.org/10.36907/KRIVET.2020.23.1.39