DOI QR코드

DOI QR Code

AI 비지도 학습 기반의 학교폭력 예방 데이터 분석 시스템 개발

Development of a data analysis system for preventing school violence based on AI unsupervised learning

  • 투고 : 2021.09.09
  • 심사 : 2021.09.17
  • 발행 : 2021.10.29

초록

학교폭력은 사회적 문제로 인식되고 있으며 이를 예방하기 위한 다양한 노력도 함께 이루어지고 있다. 본 연구에서는 학생들 상호 간의 친밀도, 대화 빈도 및 모둠 선호도 데이터를 분석함으로써 교우 관계를 파악하고 이를 통해 궁극적으로 학교폭력을 예방할 수 있는 시스템을 개발하였다. 리커트 척도 설문을 활용하여 학급 내 학생들과의 친밀도, 대화 빈도 및 모둠 선호도를 각각 수치화하였고, 설문 데이터는 K-means 알고리즘을 활용하여 적정한 개수의 클러스터로 군집화 및 시각화하였다. 담임교사는 학급 내 학생들 간의 친밀도, 대화 빈도 및 모둠 선호도 분석 데이터를 그래프의 형태로 시각적으로 확인하고, 이를 근거로 특정 그룹의 학생 개별 상담 및 학급 운영 등 학교폭력 예방을 위한 참고 자료로 활용 가능하다. 데이터 분석 결과는 기존에 교사가 학생 관찰등의 방법으로 정성적으로 파악하고 있던 교우 관계와 상당 부분 일치하였고, 이는 본 데이터 분석 시스템이 담임교사의 학급 내 교우 관계 파악을 위한 정량적 근거 자료로 유의미하게 활용될 수 있음을 의미한다. 한계점은 학생들의 주관적인 기준으로 인해 설문 결과가 왜곡될 수 있는 점이다. 본 연구가 담임교사의 학급 내 교우 관계 파악 및 학교폭력 예방 노력에 실질적인 도움을 제공하며 학교폭력 예방에 기여하기를 기대한다.

School violence has long been recognized as a social problem, and various efforts have been made to prevent it. In this study, we propose a system that can prevent school violence by analyzing data on the frequency of conversations between students, friendship and preference to be in the same group. This data was quantified using a Likert scale questionnaire, and also grouped into the appropriate number of clusters using the K-means algorithm. Additionally, the homeroom teacher observed the frequency and nature of conversations between students, and targeted specific individuals or groups for counseling and intervention, with the aim of reducing school violence. Data analysis revealed that the teachers' qualitative observations were consistent with the quantified data based on student questionnaires, and therefore applicable as quantitative data towards the identification and understanding of student relationships within the classroom. The study has potential limitations. The data used is subjective and based on peer evaluations which can be inconsistent as the students may use different criteria to evaluate one another. It is expected that this study will help homeroom teachers in their efforts to prevent school violence by understanding the relationships between students within the classroom.

키워드

참고문헌

  1. Park, H.J, Jung, M.K and Kim, H.W.(2010). The Effect of the School Violence Prevention Program at the Elementary School Level. The Journal of Korean Education, 37(4), 47-72.
  2. Kwon, M.S.(2005). Friendship improvement method search on rejected children's of sociometric rating in Classroom. The Journal of korean educational forum, 4(2): 1-2.
  3. Ko, S.H, Yoon, U.N, Jumabek Alikhanov and Jo, G.S.(2017). Improved CS-RANSAC Algorithm Using K-Means Clustering. KIPS Transactions on Software and Data Engineering, 6(6), 315-320. https://doi.org/10.3745/KTSDE.2017.6.6.315
  4. Woo, J.A.(2005). The effects of the closeness and the qualitative characteristics of peer relationship on the school adjustment in elementary school. Busan National University of Education.
  5. Jung, M.Y, Kim, M.S, Song, J.W.(2020). A Study on the Color Analysis to the Illustration of Music Textbook in 3rd-4th Grade Elementary School Using Machine Learning. The Korean Journal of Arts Education, 18(2), 93-118.
  6. Yoon, C.H, Park, S.G, and Shin, I.S.(2014). A Meta-Analysis of the Effects of School Violence Prevention Programs in Korea. Asian Journal of Education, 15(1), 189-215. https://doi.org/10.15753/aje.2014.15.1.009
  7. Park, E.Y.(2019). Do it! Jump to python. easyspublishing.
  8. Hong, G.C.(2002). The Effect of Friendships Improvement Program on Bullying Decrease in School. THESIS COLLECTION, 37.-: 169-209.
  9. Kim, K.T, Lee, B.H.(2014). A Study of Teacher Leadership for Preventing School Violence from the Perspective of the Analects of Confucian. Teacher Education Research, 53(2), 321-333. https://doi.org/10.15812/TER.53.2.201406.321
  10. Park, H.B.(2012). School Violence Prevention through Improving Teacher's Empathy Ability. Journal of Ethics Education Studies, 28(0), 45-62.
  11. Koo, D.H, Kim, D.J.(2020). Data science education program based on problem solving learning. The Journal of Korea elementary education, 31, Supplement, 203-215.
  12. Lee, Y.H, Koo, D.H.(2017). A Study on Development Deep Learning Based Learning System for Enhancing the Data Analytical Thinking. Korean Association of Information Education, 21(4), 393-401. https://doi.org/10.14352/jkaie.21.4.393
  13. Park, H.C, Jo, G.H.(2017). Waste Database Analysis Using K-means Clustering by Data Fusion, Journal of the Korean Data Analysis Society, 7(4), 1271-1279.
  14. Lim, S.Y, Kang, N.R and Kwack, Y.S.(2018). Effects of a Class-Based School Violence Prevention Program for Elementary School Students. Child and Adolescent Psychiatry, 29(2), 54-61.
  15. Kim, K.E.(2016). CRISIS of KOREAN Education, School Violence : How Should It Be Treated?. International Journal of Crisis & Safety, 1(1) : 30-35.
  16. Kwon, H.C.(2012). A Study of Gifted Students' Peer Relationship in an Elementary School's General and Gifted Classes via SNA(Social Network Analysis). The Graduate School Chonbuk National University.