SVM (Support Vector Machine) 방법을 이용한 한국의 Affirmative Action 기반 영향 요인 연구

• 영문명: Application of Support Vector Machine Model to Analyze the Factors Influencing the Foundation of Affirmative Action in the Field of Education in Korea
• 발행기관: 한국비교정부학회
• 저자명: 장지현(Ji-Hyun Jang)
• 간행물 정보: 『한국비교정부학보』제28권 제1호, 41~60쪽, 전체 20쪽
• 주제분류: 사회과학 > 행정학
• 파일형태: PDF
• 발행일자: 2024.03.30

영문 초록

(Purpose) This study aims to examine the factors influencing the foundational aspects of Affirmative Action in the Korean educational sector, to determine their relative importance, and to analyze how the characteristics of Affirmative Action measures vary according to the characteristics of these influencing factors. (Design/methodology/approach) The data for this analysis is derived from a 2022 survey conducted by the Korea Institute of Public Administration, targeting the entire population, and employs the Support Vector Machine (SVM) method from machine learning for the analysis. (Findings) The analysis shows that the importance of factors influencing the foundation of Affirmative Action are in the order of household income, region, education level, gender, occupation, and age. As for the interaction effects of the independent variables, a more positive perception of the foundation for Affirmative Action is observed in rural areas compared to urban areas. Additionally, from the perspective of household income, it can be said that individuals with incomes in the range of 1 to 2 million KRW, which indicates a lower income level, support the active introduction of programs based on these measures. (Research implications or Originality) These results suggest that when applying Affirmative Action policies in the educational sector, it is necessary to choose a differentiated, customized approach that considers characteristics by income level, region, gender, and age.

목차

Ⅰ. 서론

Ⅱ. 이론적 논의

Ⅲ. 조사 설계

Ⅳ. 분석결과

Ⅴ. 결론

References

키워드

머신러닝 서포트 벡터머신 모형 교육 분야 Affirmative Action 빅데이터 분석 Machine Learning Support Vector Machine Affirmative Action Affirmative Action in the Field of Education Big Data Analysis