Classification of Mental Health Level of Students Using SMOTE and Soft Voting Ensemble Classifier and the DASS-21 Profile
This study proposes a comprehensive approach to address the rise in mental health problems among college students. It leverages the Synthetic Minority Over-sampling Technique (SMOTE) to address the class imbalance in the dataset and employs a Voting Ensemble with soft voting to combine several base...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
INTI International University
|
| Subjects: | |
| Online Access: | http://eprints.intimal.edu.my/2194/ http://eprints.intimal.edu.my/2194/1/747 http://eprints.intimal.edu.my/2194/2/ij2025_38.pdf |
| _version_ | 1848766990015004672 |
|---|---|
| author | Muhammad Imron, Rosadi Khoirun, Nisa Nanik, Kholifah |
| author_facet | Muhammad Imron, Rosadi Khoirun, Nisa Nanik, Kholifah |
| author_sort | Muhammad Imron, Rosadi |
| building | INTI Institutional Repository |
| collection | Online Access |
| description | This study proposes a comprehensive approach to address the rise in mental health problems among college students. It leverages the Synthetic Minority Over-sampling Technique (SMOTE) to address the class imbalance in the dataset and employs a Voting Ensemble with soft voting to combine several base algorithms (Logistic Regression, Random Forest, Gradient Boosting, and XGBoost/SVM) for accurate prediction of mental health levels (normal, mild, moderate, severe, very severe). Feature importance-based feature selection using Random Forest is utilized to eliminate less relevant attributes. The model evaluation includes accuracy, precision, recall, F1-score, and confusion matrix analysis. The results demonstrate that the ensemble approach improves stability and accuracy compared to individual models. Notably, the application of SMOTE led to significant performance improvements, with classification accuracies reaching up to 100% for the Random Forest model. These findings support the use of ensemble learning and SMOTE for developing effective college student mental health screening systems, ultimately enabling timely intervention and support |
| first_indexed | 2025-11-14T11:59:55Z |
| format | Article |
| id | intimal-2194 |
| institution | INTI International University |
| institution_category | Local University |
| language | English English |
| last_indexed | 2025-11-14T11:59:55Z |
| publisher | INTI International University |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | intimal-21942025-10-23T09:38:39Z http://eprints.intimal.edu.my/2194/ Classification of Mental Health Level of Students Using SMOTE and Soft Voting Ensemble Classifier and the DASS-21 Profile Muhammad Imron, Rosadi Khoirun, Nisa Nanik, Kholifah QA75 Electronic computers. Computer science QA76 Computer software T Technology (General) This study proposes a comprehensive approach to address the rise in mental health problems among college students. It leverages the Synthetic Minority Over-sampling Technique (SMOTE) to address the class imbalance in the dataset and employs a Voting Ensemble with soft voting to combine several base algorithms (Logistic Regression, Random Forest, Gradient Boosting, and XGBoost/SVM) for accurate prediction of mental health levels (normal, mild, moderate, severe, very severe). Feature importance-based feature selection using Random Forest is utilized to eliminate less relevant attributes. The model evaluation includes accuracy, precision, recall, F1-score, and confusion matrix analysis. The results demonstrate that the ensemble approach improves stability and accuracy compared to individual models. Notably, the application of SMOTE led to significant performance improvements, with classification accuracies reaching up to 100% for the Random Forest model. These findings support the use of ensemble learning and SMOTE for developing effective college student mental health screening systems, ultimately enabling timely intervention and support INTI International University Article PeerReviewed text en cc_by_4 http://eprints.intimal.edu.my/2194/1/747 text en cc_by_4 http://eprints.intimal.edu.my/2194/2/ij2025_38.pdf Muhammad Imron, Rosadi and Khoirun, Nisa and Nanik, Kholifah Classification of Mental Health Level of Students Using SMOTE and Soft Voting Ensemble Classifier and the DASS-21 Profile. INTI JOURNAL, 2025 (38). pp. 1-6. ISSN e2600-7320 https://intijournal.intimal.edu.my |
| spellingShingle | QA75 Electronic computers. Computer science QA76 Computer software T Technology (General) Muhammad Imron, Rosadi Khoirun, Nisa Nanik, Kholifah Classification of Mental Health Level of Students Using SMOTE and Soft Voting Ensemble Classifier and the DASS-21 Profile |
| title | Classification of Mental Health Level of Students Using SMOTE and Soft Voting Ensemble Classifier and the DASS-21 Profile |
| title_full | Classification of Mental Health Level of Students Using SMOTE and Soft Voting Ensemble Classifier and the DASS-21 Profile |
| title_fullStr | Classification of Mental Health Level of Students Using SMOTE and Soft Voting Ensemble Classifier and the DASS-21 Profile |
| title_full_unstemmed | Classification of Mental Health Level of Students Using SMOTE and Soft Voting Ensemble Classifier and the DASS-21 Profile |
| title_short | Classification of Mental Health Level of Students Using SMOTE and Soft Voting Ensemble Classifier and the DASS-21 Profile |
| title_sort | classification of mental health level of students using smote and soft voting ensemble classifier and the dass-21 profile |
| topic | QA75 Electronic computers. Computer science QA76 Computer software T Technology (General) |
| url | http://eprints.intimal.edu.my/2194/ http://eprints.intimal.edu.my/2194/ http://eprints.intimal.edu.my/2194/1/747 http://eprints.intimal.edu.my/2194/2/ij2025_38.pdf |