应对(心理学)
心理学
单变量
探索性研究
应用心理学
压力(语言学)
认知心理学
可视化
压力测试
探索性因素分析
预测能力
心理健康
支持向量机
临床心理学
发展心理学
预测效度
心理测量学
人工智能
感知压力量表
社会心理学
心理压力
机器学习
解码方法
数据科学
作者
Jeahong Kim,Minwoo Jo,Sooleen Nam,Yujin Lee,Yeonji Baik
标识
DOI:10.1016/j.chbr.2025.100902
摘要
Current study examined the validity of a digitalized Person-in-the-Rain test (dPITR) in assessing stress and coping abilities using traditional univariate and machine learning methods. By analyzing drawings and comparing results with established self-reported measures (Perceived Stress Scale and Ways of Coping Questionnaire), the study identifies significant relationships between drawing features and stress and coping scores. Machine learning models (K-Nearest Neighbor, Support Vector Machine, Random Forest) revealed complex, non-linear patterns, with stress-related features showing significant predictive power for perceived stress and coping styles. The findings support dPITR as a reliable, non-invasive tool for assessing psychological constructs and highlight the value of integrating advanced analytics in psychological assessments. This digital approach offers promising applications for scalable and precise mental health evaluations. • Digital Person-in-the-Rain (dPITR) test validates stress and coping responses. • dPITR stress scores positively correlate with negative stress perception. • Machine learning reveals complex stress-coping patterns beyond univariate analysis. • Deep learning identifies key drawing features associated with stress and coping levels. • dPITR enables rapid and objective stress pre-screening across various settings.
科研通智能强力驱动
Strongly Powered by AbleSci AI