What does this research mean for the field?

School psychological climate, depression, and parental loneliness are the primary predictors of positive youth development in Chinese adolescents, with distinct developmental pathways varying significantly by age and demographic background. Novelty: ClaimNovelty.NOVEL_FINDING. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

Identify nonlinear, high-dimensional predictors of positive youth development over time using machine learning algorithms in a large adolescent cohort.

September 7, 2026Applied Psychology Health and Well-Being

Predicting positive youth development among Chinese adolescents: A machine learning approach using multiwave longitudinal data

View Full Paper

Ask AI

Bookmark

Authors

ZLZelin Liu ZLZékai Lu YWYaqiong Wang

Discussion

Member takes

Overview

Longitudinal study reveals key nonlinear predictors of youth development in Chinese adolescents, highlighting the need for context-sensitive interventions.

Key Points

Identify nonlinear, high-dimensional predictors of positive youth development over time using machine learning algorithms in a large adolescent cohort.
Analyzed four-wave longitudinal survey data from 5,019 Chinese adolescents aged 9–19.
Evaluated 12 machine learning algorithms to predict wave 4 positive youth development using the Chinese 4Cs model (Character, Competence, Confidence, Connection), controlling for wave 3 baseline scores.
Applied SHAP (SHapley Additive exPlanations) analysis to determine feature importance across different age groups and student classifications.
CatBoost emerged as the top-performing algorithm among the 12 tested models, achieving a predictive score of 0.816.
SHAP feature attribution identified school psychological climate, depression, and parental loneliness as the top three overall predictors of youth development.
Age and demographic analyses revealed that school climate was most influential for primary and middle schoolers, parental loneliness predominated for high schoolers, and distinct aspirational, relational, and clinical pathways characterized migrant, left-behind, and rural adolescents, respectively.

Cite This Study

Liu et al. (2026) studied this question.

synapsesocial.com/papers/6a9e85a2c3034f961570deec https://doi.org/10.1111/aphw.70211

View Full Paper

Ask AI

Bookmark

September 7, 2026Applied Psychology Health and Well-Being

Predicting positive youth development among Chinese adolescents: A machine learning approach using multiwave longitudinal data

View Full Paper

Ask AI

Bookmark

Authors

ZLZelin Liu ZLZékai Lu YWYaqiong Wang

Discussion

Member takes

Overview

Longitudinal study reveals key nonlinear predictors of youth development in Chinese adolescents, highlighting the need for context-sensitive interventions.

Key Points

Identify nonlinear, high-dimensional predictors of positive youth development over time using machine learning algorithms in a large adolescent cohort.
Analyzed four-wave longitudinal survey data from 5,019 Chinese adolescents aged 9–19.
Evaluated 12 machine learning algorithms to predict wave 4 positive youth development using the Chinese 4Cs model (Character, Competence, Confidence, Connection), controlling for wave 3 baseline scores.
Applied SHAP (SHapley Additive exPlanations) analysis to determine feature importance across different age groups and student classifications.
CatBoost emerged as the top-performing algorithm among the 12 tested models, achieving a predictive score of 0.816.
SHAP feature attribution identified school psychological climate, depression, and parental loneliness as the top three overall predictors of youth development.
Age and demographic analyses revealed that school climate was most influential for primary and middle schoolers, parental loneliness predominated for high schoolers, and distinct aspirational, relational, and clinical pathways characterized migrant, left-behind, and rural adolescents, respectively.

Cite This Study

Liu et al. (2026) studied this question.

synapsesocial.com/papers/6a9e85a2c3034f961570deec https://doi.org/10.1111/aphw.70211

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark