适应性
回归分析
树(集合论)
心理学
回归
数学教育
统计
数学
管理
经济
数学分析
作者
Xiujun Li,Tao Wei,Zhang Jing,Jin Luo,Yang Cai,Mianlin Deng,Lulu Hou,Yongyong Yang,Dezhen Xu,Gong Wang,Wendian Shi
标识
DOI:10.1108/et-03-2024-0108
摘要
Purpose We seek to systematically explore the joint effects of individual and environmental factors on college students’ career adaptability. Design/methodology/approach This study employed convenience sampling to collect individual and environmental data from 2,021 college students. The interaction between individual and environmental factors affecting the career adaptability of college students was then analyzed based on a regression tree model. Factors including emotional intelligence, cognitive flexibility, personality traits, role accumulation, experience (internships) and skills (professional certificates), parenting styles, family socioeconomic status and social support were included in the analysis. Findings Among the initial 20, the regression tree model identified seven key variables (emotional intelligence, conscientiousness, emotional warmth, number of certificates, openness, career-related support from teachers and cognitive flexibility) as significant. Emotional intelligence emerged as the most influential factor in predicting college students’ career adaptability. The samples were segmented into 16 subgroups based on the interactions among these variables. College students with high emotional intelligence and substantial support from parents and teachers exhibited maximum levels of career adaptability, while those with low emotional intelligence and lacking conscientiousness demonstrated the lowest levels of career adaptability. Originality/value This study represents the first instance of using machine learning methods to systematically investigate the joint effects of individual and environmental factors on college students’ career adaptability. The decision tree model established in this study can identify the unique characteristics exhibited by individuals at different career adaptability levels, offering opportunities to discover the boundary conditions for enhancing career adaptability.
科研通智能强力驱动
Strongly Powered by AbleSci AI