DOI QR코드

DOI QR Code

A Deep Learning-based Regression Model for Predicting Government Officer Education Satisfaction

공무원 직무 전문교육 만족도 예측을 위한 딥러닝 기반 회귀 모델 설계

  • 오수민 (서울여자대학교 데이터사이언스학과) ;
  • 윤성연 (서울여자대학교 데이터사이언스학과) ;
  • 박민서 (서울여자대학교 데이터사이언스학과)
  • Received : 2024.05.21
  • Accepted : 2024.09.01
  • Published : 2024.09.30

Abstract

Professional job training for government officers emphasizes establishing desirable values as public officials and improving professionalism in public service. To provide customized education, some studies are analyzed factors affecting education satisfaction. However, there is a lack of research predicting education satisfaction with educational contents. Therefore, we propose a deep learning-based regression model that predicts government officer education satisfaction with educational contents. We use education information data for government officer. We use one-hot encoding to categorize variables collected in text format, such as education targets, education classifications, and education types. We quantify the education contents stored in text format as TF-IDF. We train our deep learning-based regression model and validate model performance with 10-Fold Cross Validation. Our proposed model showed 99.87% accuracy on test sets. We expect that customized education recommendations based on our model will help provide and improve optimized education content.

공직자로서의 바람직한 가치관 확립과 공직의 전문성 향상을 위해 공무원의 직무 전문교육이 강조되고 있다. 만족도 높은 맞춤형 직무교육을 제공하기 위해 만족도에 영향을 미치는 요인을 분석한 연구들이 제안되고 있으나, 교육 내용을 활용하여 만족도를 예측한 연구는 부족한 실정이다. 따라서 본 연구는 교육 내용을 함께 고려해 공무원 직무 전문교육 만족도를 예측하는 딥러닝(Deep Learning) 모델을 제안한다. 제안 방법은 공무원 전문 교육과정 정보데이터를 활용한다. 우선 문자형으로 수집된 변수인 교육 대상, 교육 구분, 교육 형태를 원-핫 인코딩(One-hot Encoding)으로 카테고리화(Categorized)한다. 교육을 통해 학습할 수 있는 내용이 문자형으로 저장된 교육 내용을 TF-IDF(Term Frequency-Inverse Document Frequency)으로 수치화한다. 이를 딥러닝 기반의 회귀 모델로 학습하고, 10-겹 교차 검증(10-Fold Cross Validation)으로 모델의 성능을 검증한다. 본 연구의 제안 모델은 테스트 데이터에서 99.87%의 높은 예측 정확도를 보인다. 향후 본 연구를 고려한 맞춤형 교육 추천은 교육 대상에 최적화된 교육을 제공 및 개선하는 데에 도움이 될 것으로 기대한다.

Keywords

References

  1. Seoul Social Economy Center. Available online: https://sehub.net (accessed on 20 June 2024)
  2. Korean Statistical Information Service (KOSIS). Available online: https://kosis.kr (accessed on 20 June 2024)
  3. Industrial Skills Council (ISC). Available online: https://www.isckorea.or.kr (accessed on 20 June 2024)
  4. J. Lee & H. Jang, "Current Status and Policy Issues of Collaborations between Universities and Family Companies in Korea", Journal of the Economic Geographical Society of Korea, Vol. 23, No. 1, pp. 71-81, 2020. DOI: 10.23841/egsk.2020.23.1.71
  5. Korea Asset Management Corporation (KAMCO) Human Resources Development Institute. Available online: https://hrd.kamco.or.kr (accessed on 20 June 2024)
  6. I.M.K. Ho, K.Y. Cheong, and A. Weldon, "Predicting student satisfaction of emergency remote learning in higher education during COVID-19 using machine learning techniques", PLOS ONE, Vol. 16, No. 4, April 2021. DOI: 10.1371/journal.pone.0249423
  7. I. Sahin, "Predicting student satisfaction in distance education and learning environments", Turkish Online Journal of Distance Education (TOJDE), Vol. 8, No. 2, pp. 113-119, April 2007.
  8. Y. Han, "A Study on the Factors affecting Korean Medical Students' Satisfaction with Education", The Journal of the Convergence on Culture Technology (JCCT), Vol. 10, No. 3, pp. 253-258, 2024. DOI: 10.17703/JCCT.2024.10.3.253
  9. H. Kim, "The Efficacy of Zoom Technology as an Educational Tool for English Reading Comprehension Achievement in EFL Classroom", International Journal of Advanced Culture Technology (IJACT), Vol. 8, No.3, pp. 198-205, 2020. DOI: 10.17703/IJACT.2020.8.3.198
  10. T. Cho, "Exploratory Analysis on Strengthening Public Professionalism: Focusing on Institution for Improving Public Professionalism", Institute of Public Policy and Administration, Vol. 34, No. 1, pp 101-129, March 2020. DOI: 10.17327/ippa.2020.34.1.005
  11. Korea Law Information Center. Available Online: https://www.law.go.kr (accessed on 20 June 2024)
  12. A. Akiko, "An information-theoretic perspective of tf-idf measures", Information Processing& Management, Vol. 39, No. 1, pp. 45-65, 2003. DOI: 10.1016/S0306-4573(02)00021-3