한국전자거래학회지 (The Journal of Society for e-Business Studies)

  • 제22권4호
  • /
  • Pages.193-214
  • /
  • 2017
  • /
  • 2288-3908(pISSN)
  • /
  • 2765-3846(eISSN)
한국전자거래학회 (Society for e-Business Studies)
권호 표지
DOI QR코드

DOI QR Code

토픽모델링을 활용한 소프트웨어 분야 대학 교과과정 분석

A Comparative Analysis of Curriculums for Software-related Departments based on Topic Modeling

  • 투고 : 2017.11.06
  • 심사 : 2017.11.28
  • 발행 : 2017.11.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

소프트웨어 직무의 특성과 대학교의 SW 학과가 개발한 커리큘럼 간의 차이가 존재하는 현재에서, 실제로 SW 관련 교과과정 편성이 어떻게 구성되어 있는지, 그리고 현실적으로 SW 인력의 실무 요구사항과 부적합한 부분을 확인하는 것이 매우 중요한 시기이다. 해외 사례를 보면 이미 실무 요구사항 중심의 SW 교육을 바탕으로 SW 인력을 양성하려는 노력이 진행되어 오고 있다. 그 결과 실제 관련 실무 기업들의 채용에 대한 긍정적인 반응이 나타나고 있다. 국내에서도 정부 주도하에 이러한 시도가 시도되고 있으며 특히 SW 중심대학 사업을 바탕으로 관련 분야의 선도대학의 역할을 부여하고 있다. 그러나 SW 분야의 인력 공급 문제는 여전히 실무분야와 교육 분야의 이슈가 되고 있다. 교과과정 구성에 대한 실무 기업들의 관점의 환경적 요소가 확실히 반영되지 못하고 있다는 기존의 한계에 따라 본 연구에서는 교육 내용의 구성과 실무의 차이를 줄일 수 있는 방법을 진단하고자 하였다. 그에 따라 실제 활용중인 대학의 교과과정과 강의계획서 자료를 바탕으로 토픽모델링을 실시함으로서 교과과정과 강의계획서에 대한 키워드를 도출하였다. 분석 결과 분석에 활용된 관련 대학 학과의 실습 비율이 상대적으로 낮은 수준을 보였으며 교과목 중첩비율, 강의계획서 키워드 중첩비율도 일반 수준으로 보여짐에 따라서 체계적인 교과과정 확립과 실무 능력 배양을 위한 강의계획 수립이 중요하다는 것을 확인하였다.

It is a very important time to check how SW curriculum is actually organized and what is inadequate to practical requirements of SW manpower in the present situation where there is a difference of viewpoints between software field and SW curriculum of university. In overseas cases, efforts have already been made to cultivate SW manpower based on SW training centered on practical requirements. As a result, there is a positive response to the recruitment of actual related companies. In Korea, these attempts have been attempted under government initiative. In particular, based on the SW-centered university project, it has given the role of a leading university in related fields. However, with regard to the labor supply problem in the SW sector, the requirements of the business enterprises still differ from the educational curriculum. In this study, we tried to diagnose the method that can reduce the difference between the composition and the practice of the contents according to the existing limit that the environment factor of the viewpoint of the working companies about the curriculum composition is not clearly reflected. As a result, the topic modeling based on the university's curriculum and lecture plan data is used to derive keywords for curriculum and lecture plan. Through the data analysis, this study confirmed that the practice rate of related university departments utilized in data analysis is relatively low. In addition, we found that it is important to establish a systematic curriculum and to build a lecture plan to cultivate practical skills, as the number of overlapping textbooks and the number of keyword overlapping are found.

키워드

참고문헌

  1. Amit, S., "Modern Information Retrieval: A Brief Overview," Bulletin of the IEEE Computer Society Technical Committee on Data Engineering, Vol. 24, No. 4, pp. 35-43, 2001.
  2. Blei, D., Ng, A. and Jordan, M., 'Latent Dirichlet Allocation,' Journal of Machine Learning Research, Vol. 3(2003), pp. 993-1022.
  3. Cha, J. S., “The Study of the Field Customized SW Training Course Design based on the Analysis of the Field Suitability of the University SW Education,” Smart Media Journal, Vol. 4, No. 4, pp. 86-92, 2015.
  4. Duan, Y. and Cruz, C., “Formalizing Semantic of Natural Language through Conceptualization from Existence,” International Journal of Innovation, Vol. 2, No. 1, pp. 37-42, 2011.
  5. Feldman, R. and Sanger, J., "The Text Mining Handbook: Advanced Approaches in Analyzing Unstructured Data," Cambridge University Press, 2007.
  6. Han, D. S., "University Education and Contents in The Fourth Industrial Revolution," Human Contents, Vol. 42, pp. 9-24, 2016. https://doi.org/10.18658/humancon.2016.09.42.9
  7. Harvard University, "The Unofficial Guide to Computer Science at HARVARD ver. 14," pp. 1-12, 2014.
  8. Hutchins, J., "The history of machine translation in a nutshell," pp. 1-4, 2005.
  9. Kang, S. K., Yu, H., and Lee, Y. J., “Analyzing Disaster Response Terminologies by Text Mining and Social Network Analysis,” Information Systems Review, Vol. 18, No. 1, pp. 141-155, 2016. https://doi.org/10.14329/isr.2016.18.1.141
  10. Kim, J. Y. and Kim, D. S., "A Study on the Method for Extracting the Purpose-Specific Customized Information from Online Product Reviews based on Text Mining," The Journal of Society for e-Business Studies, Vol. 21, No. 2, pp. 151-161, 2016. https://doi.org/10.7838/JSEBS.2016.21.2.151
  11. Kim, S. K., Cho, H. J., and Kang, J. Y., “The Status of Using Text Mining in Academic Research and Analysis Methods,” Journal of Information Technology and Architecture, Vol. 13, No. 2, pp. 317-329, 2016.
  12. Kishorjit, N., Vidya Raj R. K., Nirmal, Y., and Sivaji, B., "Manipuri Morpheme Identification," Proceedings of the 3rd Workshop on South and Southeast Asian Natural Language Processing(SANLP), pp. 95-108, 2012.
  13. Lee, K. N., "SW manpower employment trend," Information and communication broadcasting policy, Vol. 25, No. 6, pp. 39-46.
  14. Manning and Schutze, "Foundations of Statistical Natural Language Processing," MIT Press, 1999.
  15. Ministry of Science, ICT and Future Planing, "Annual Report on Information Technology Development," National IT Industry Promotion Agency, pp. 1-341, 2015.
  16. Noh, Y., Ahn, I. J., and Choi, S. K., “A Study on Analyzing and Developing the Syllabus for Library and Information Science Core Courses,” Journal of Korean Library and Information Science Society, Vol. 44, No. 1, pp. 143-175, 2013. https://doi.org/10.16981/kliss.44.1.201303.143
  17. Ryu, J. S., Lee, S. H., and Kim, J. W., "A Study on the Problems of Korean University Education for the Promotion of IT Talent," Samsung Economic Research Institute, pp. 1-189, 2011.
  18. Sidorov, G., Gelbukh, A., Gomez-Adorno, H., and Pinto, D., "Soft Similarity and Soft Cosine Measure: Similarity of Features in Vector Space Model," Computacion y Sistemas, Vol. 18, No. 3, pp. 491-504, 2014.
  19. Spruill, M. C., "Asymptotic Distribution of Coordinates on High Dimensional Spheres," Electronic Communications in Probability, Vol. 12, pp. 234-247, 2007. https://doi.org/10.1214/ECP.v12-1294
  20. Sullivan, D., "Document Warehousing and Text Mining: Techniques for Improving Business Operations, Marketing, and Sales," John Wiley & Sons, Inc., pp. 1-560, 2001.
  21. Tan, A. H., "Text Mining: The State of the Art and the Challenges," Proceedings of the PAKDD 1999 Workshop on Knowledge Discovery from Advanced Databases, Vol. 8, pp. 1-6, 1999.
  22. Tseng, Y. H., Lin, C. J., and Lin, Y. I., “Text Mining Techniques for Patent Analysis,” Information Processing & Management, Vol. 43, No. 5, pp. 1216-1247, 2007. https://doi.org/10.1016/j.ipm.2006.11.011
  23. Weiss, S. M., Apte, C., Damerau, F. J., Johnson, D. E., Oles, F. J., Goetz, T., and Hampp, T., "Maximizing Text-Mining Performance," IEEE Intelligent Systems, Vol. 14, No. 4, pp. 63-69, 1999.

피인용 문헌

  1. 빅데이터 분석을 통한 지방자치단체 정책이슈 도출 방법론 vol.18, pp.10, 2017, https://doi.org/10.5392/jkca.2018.18.10.229
  2. 계열별 학습자 분석 기반의 컴퓨팅사고력 연구 vol.24, pp.4, 2017, https://doi.org/10.7838/jsebs.2019.24.4.017
  3. 토픽 모델링을 이용한 컴퓨팅 사고력 관련 연구 동향 분석 vol.23, pp.6, 2019, https://doi.org/10.14352/jkaie.2019.23.6.607