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

<p>We investigate the viability of using data mining technologies to identify college students’ mental health issues in light of the rising number of these issues. To address the limitations of the traditional Apriori algorithm in data mining of mental health problems, an improved Apriori algorithm is proposed using the classification rule mining method. The relationship between various factors and the mental health problems of college students is better explored by this algorithm. Ultimately, the mental health care pathway that was developed during the exploration was used to conduct a comparative trial between those who received mental health services and those who did not. The experimental group’s mean score in the hyperactive concentration inability dimension was 3.25 after getting mental health care for three weeks, which was 22.6% higher than the control group’s mean score. The aspects of emotional symptoms, pro-social conduct, and total difficulty score also showed significant variations (p&lt;0.05). The mean scores of the experimental group in the pro-social behavior and emotional symptoms dimension in the course of the study and the pre-experiment were 2.17 and 0.57, accordingly, which both demonstrated highly significant differences (p&lt;0.01) in the between-group comparison of the differences in scores at different evaluation times with the control group.</p>
</abstract>

We investigate the viability of using data mining technologies to identify college students’ mental health issues in light of the rising number of these issues. To address the limitations of the traditional Apriori algorithm in data mining of mental health problems, an improved Apriori algorithm is proposed using the classification rule mining method. The relationship between various factors and the mental health problems of college students is better explored by this algorithm. Ultimately, the mental health care pathway that was developed during the exploration was used to conduct a comparative trial between those who received mental health services and those who did not. The experimental group’s mean score in the hyperactive concentration inability dimension was 3.25 after getting mental health care for three weeks, which was 22.6% higher than the control group’s mean score. The aspects of emotional symptoms, pro-social conduct, and total difficulty score also showed significant variations (p<0.05). The mean scores of the experimental group in the pro-social behavior and emotional symptoms dimension in the course of the study and the pre-experiment were 2.17 and 0.57, accordingly, which both demonstrated highly significant differences (p<0.01) in the between-group comparison of the differences in scores at different evaluation times with the control group.

Path analysis of digitally empowered mental health services for university students

Applied Mathematics and Nonlinear Sciences

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

We investigate the viability of using data mining technologies to identify college students’ mental health issues in light of the rising number of these...

Path analysis of digitally empowered mental health services for university students

Publié en ligne: 31 janv. 2024

Pages: -

Reçu: 26 déc. 2023

Accepté: 05 janv. 2024

DOI: https://doi.org/10.2478/amns-2024-0284

Mots clés
Classification rule mining, Apriori algorithm, Apache Spark framework, Mental health services

© 2024 Caiyan Deng et al., published by Sciendo

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

Path analysis of digitally empowered mental health services for university students

Publié en ligne: 31 janv. 2024

Pages: -

Reçu: 26 déc. 2023

Accepté: 05 janv. 2024

DOI: https://doi.org/10.2478/amns-2024-0284

Mots clésClassification rule mining, Apriori algorithm, Apache Spark framework, Mental health services

© 2024 Caiyan Deng et al., published by Sciendo

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

Mots clés
Classification rule mining, Apriori algorithm, Apache Spark framework, Mental health services