Understanding the mental health effects of social support among university students: a hybrid SEM–ANN approach

Physical fitness test results are an important indicator of college students’ physical condition. After officially enrolling, Chinese college students undergo physical training, which not only greatly improves their fitness, but also helps cultivate discipline and stress resilience. At the same time, the transition into university life may pose psychological challenges for some students. Social support has been widely recognized as a key protective factor for mental health during demanding transitional periods. However, the psychological mechanisms through which social support is associated with university students’ mental health remain insufficiently understood. This study examines the association between social support and university students’ mental health, with a particular focus on the mediating roles of self-efficacy, emotion regulation, and coping strategies. A structured questionnaire was administered to 557 students, capturing self-reported responses across five key constructs: social support, mental health, self-efficacy, emotion regulation, and coping strategies. Data were collected shortly after university enrollment, following the completion of the early-term physical training period in China. A two-stage hybrid method combining Structural Equation Modeling (SEM) and Artificial Neural Networks (ANN) was employed to examine linear associations and the relative importance of key psychological predictors of mental health. The results revealed that emotion regulation, self-efficacy, and coping strategies significantly influence mental health, and all three serve as mediators in the relationship between social support and mental health. Moreover, the normalized importance values derived from the multilayer perceptron model identified emotion regulation (100%), self-efficacy (80.7%), and coping strategies (70.1%) as the most critical predictors of mental health among university students. This study demonstrates that social support is indirectly associated with university students’ mental health through emotion regulation, self-efficacy, and coping strategies. The results advance understanding of the psychological mechanisms linking social support and mental health during the early stage of university adjustment and provide practical insights for designing targeted interventions to strengthen psychological resources and enhance student well-being.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-04-28
DOI
https://doi.org/10.1038/s41598-026-48998-y
Primary Topic
Mental Health via Writing
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Understanding the mental health effects of social support among university students: a hybrid SEM–ANN approach

Shanliang Wang, Lanying Yao
Scientific Reports
Mental Health via Writing
article

Understanding the mental health effects of social support among university students: a hybrid SEM–ANN approach

Shanliang Wang, Lanying Yao
article en

Abstract

Physical fitness test results are an important indicator of college students’ physical condition. After officially enrolling, Chinese college students undergo physical training, which not only greatly improves their fitness, but also helps cultivate discipline and stress resilience. At the same time, the transition into university life may pose psychological challenges for some students. Social support has been widely recognized as a key protective factor for mental health during demanding transitional periods. However, the psychological mechanisms through which social support is associated with university students’ mental health remain insufficiently understood. This study examines the association between social support and university students’ mental health, with a particular focus on the mediating roles of self-efficacy, emotion regulation, and coping strategies. A structured questionnaire was administered to 557 students, capturing self-reported responses across five key constructs: social support, mental health, self-efficacy, emotion regulation, and coping strategies. Data were collected shortly after university enrollment, following the completion of the early-term physical training period in China. A two-stage hybrid method combining Structural Equation Modeling (SEM) and Artificial Neural Networks (ANN) was employed to examine linear associations and the relative importance of key psychological predictors of mental health. The results revealed that emotion regulation, self-efficacy, and coping strategies significantly influence mental health, and all three serve as mediators in the relationship between social support and mental health. Moreover, the normalized importance values derived from the multilayer perceptron model identified emotion regulation (100%), self-efficacy (80.7%), and coping strategies (70.1%) as the most critical predictors of mental health among university students. This study demonstrates that social support is indirectly associated with university students’ mental health through emotion regulation, self-efficacy, and coping strategies. The results advance understanding of the psychological mechanisms linking social support and mental health during the early stage of university adjustment and provide practical insights for designing targeted interventions to strengthen psychological resources and enhance student well-being.

Scientific Reports
Jiaxing Vocational Technical College (CN)
Openalex Percentile: Top 4%
Mental Health via Writing
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.