<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>This paper analyzes the social network, explores the association structure in the social network, optimizes the classical social network mining algorithm by combining the penalty matrix, and constructs the mining algorithm for students’ mental health status based on the social network by using the penalty matrix for clustering inference. On this basis, the constructed algorithm is verified by combining quality index, performance index and modularity, and the mining of students’ mental health status and mental health influencing factors is carried out to explore the teaching mechanism of school mental health education from the side. The results show that the mental health social network has a total of 50 nodes and 169 edges, and the module degree is generally in (0.4,0.9), which is reasonably divided, and is in the subhealth condition, and the mental disorder situation accounts for more. The correlation of students’ mental health is mostly distributed between (2,5), and the correlation coefficients of environmental changes, academic expectations, interpersonal relationships, self-perception, psychological conflicts, life events, family environment, and economic situation with students’ mental health are all greater than 0.5 so that the mechanism of teaching mental health education in schools is a home-school-society linkage mechanism.</p>
</abstract>

This paper analyzes the social network, explores the association structure in the social network, optimizes the classical social network mining algorithm by combining the penalty matrix, and constructs the mining algorithm for students’ mental health status based on the social network by using the penalty matrix for clustering inference. On this basis, the constructed algorithm is verified by combining quality index, performance index and modularity, and the mining of students’ mental health status and mental health influencing factors is carried out to explore the teaching mechanism of school mental health education from the side. The results show that the mental health social network has a total of 50 nodes and 169 edges, and the module degree is generally in (0.4,0.9), which is reasonably divided, and is in the subhealth condition, and the mental disorder situation accounts for more. The correlation of students’ mental health is mostly distributed between (2,5), and the correlation coefficients of environmental changes, academic expectations, interpersonal relationships, self-perception, psychological conflicts, life events, family environment, and economic situation with students’ mental health are all greater than 0.5 so that the mechanism of teaching mental health education in schools is a home-school-society linkage mechanism.

Exploring the Teaching Mechanism of School Mental Health Education Based on Social Networks

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

This paper analyzes the social network, explores the association structure in the social network, optimizes the classical social network mining algorithm by...

Exploring the Teaching Mechanism of School Mental Health Education Based on Social Networks

Data publikacji: 20 gru 2023

Zakres stron: -

Otrzymano: 13 lut 2023

Przyjęty: 30 cze 2023

DOI: https://doi.org/10.2478/amns.2023.2.01564

Słowa kluczowe
Social network, Association structure, Penalty matrix, Cluster reasoning, Mental health education

© 2023 Rong An, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Exploring the Teaching Mechanism of School Mental Health Education Based on Social Networks

Data publikacji: 20 gru 2023

Zakres stron: -

Otrzymano: 13 lut 2023

Przyjęty: 30 cze 2023

DOI: https://doi.org/10.2478/amns.2023.2.01564

Słowa kluczoweSocial network, Association structure, Penalty matrix, Cluster reasoning, Mental health education

© 2023 Rong An, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Słowa kluczowe
Social network, Association structure, Penalty matrix, Cluster reasoning, Mental health education