메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색
질문

논문 기본 정보

자료유형
학술저널
저자정보
Seon-Hi Shin (Hanyang University) Bossng Kang (Hanyang University) Myung-Suk Woo (Korea National University of Education) Youn-Ju Park (Korea National University of Education)
저널정보
한국컴퓨터교육학회 컴퓨터교육학회 논문지 컴퓨터교육학회논문지 제27권 제5호
발행연도
2024.8
수록면
67 - 78 (12page)
DOI
10.32431/kace.2024.27.5.007

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색
질문

초록· 키워드

오류제보하기
This study aimed to create machine learning-based screening tools for middle school students to predict suicide planning or attempts in school settings, and to identify the risk factors. A total of 3,812 records from a national database established through rigorous sampling designs, the 2022 Korean Youth Risk Behavior Web-based Survey (KYRBWS), were used to ensure high generalizability and minimize bias of the study’s outcomes. Five machine-learning models, utilizing various algorithms available in SAS or Python, underwent training with a 10-fold validation process. Performance evaluation included metrics such as accuracy, sensitivity, specificity, and AUC, resulting from using a common unseen test dataset. Feature importance was interpreted through the average absolute values of Shapley additive explanations (SHAP) as well as the standardized regression coefficients. The artificial neural-network model with three hidden layers and dropout layers between each dense layer emerged as the top performer. It achieved sensitivity and AUC exceeding 91%, with accuracy and specificity at 86%. However, all five models, utilizing an optimal set of nine features, demonstrated strong performance. Mental health features such as suicidal thoughts, feeling lonely, or feeling sad, and the subjective perception of dental health emerged as significant risk factors. Adolescents considering suicide were approximately 12.7 times more likely to make plans or attempt suicide than their peers without such ideation (OR = 12.7; 95% CI = [8.0-20.1]). Individuals perceiving dental health as "Very bad" were 4.4 times more prone to suicidal behavior than those with "Average" ratings (OR = 4.4; 95% CI = [1.4-13.5]). Those always feeling lonely were 2.8 times more likely to engage in suicidal behavior (OR = 2.8; 95% CI = [1.1-7.1]), while persistent feelings of sadness increased the likelihood by 1.8 times (OR = 1.8; 95% CI = [1.2-2.8]). The study also offers valuable guidance on algorithm selection and suitable options for similar applications.

목차

ABSTRACT
1. Introduction
2. Methods
3. Result
4. Discussion
5. Conclusion
References

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

최근 본 자료

전체보기

댓글(0)

0

UCI(KEPA) : I410-151-24-02-090657877