TY  - JOUR
AU  - Ahmad, Shoaib
AU  - Imran, Ali
AU  - Kshif, Tahoona
AU  - Rasheed, Zubdah Tur
AU  - Khan, Ayesha
AU  - Ali, Aamir
AU  - Ali, Muhammad
PY  - 2026
DA  - 2026/09/22
TI  - A Software-Oriented Deep Learning Framework for Multiclass Academic Stress and Mental Health Risk Prediction
JO  - ICCK Journal of Software Engineering
T2  - ICCK Journal of Software Engineering
JF  - ICCK Journal of Software Engineering
VL  - 2
IS  - 3
SP  - 220
EP  - 247
DO  - 10.62762/JSE.2026.690220
UR  - https://www.icck.org/article/abs/JSE.2026.690220
KW  - academic stress
KW  - mental health risk
KW  - deep learning
KW  - multiclass classification
KW  - BiLSTM
KW  - CatBoost
KW  - student well-being
KW  - SMOTE
KW  - predictive analytics
AB  - Student mental health and academic stress are significant concerns in higher education, creating a need for effective approaches to early risk identification. This study proposes a multiclass predictive framework for academic stress and mental health risk classification among students. The framework was developed using a Kaggle dataset containing 25,000 records with demographic, academic, behavioral, psychological, lifestyle, and medical attributes. A unified comparison was conducted across six conventional machine learning algorithms, namely Decision Tree, Random Forest, XGBoost, CatBoost, K-Nearest Neighbors (KNN), and Naïve Bayes, and three deep learning architectures, namely Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Bidirectional Long Short-Term Memory (BiLSTM). Class imbalance was addressed using the Synthetic Minority Over-sampling Technique (SMOTE), applied only to the training data, and model performance was evaluated using accuracy, precision, recall, F1-score, and confusion matrices. CatBoost and BiLSTM achieved the highest classification accuracy of 97%, with weighted F1-scores of 0.97 and macro F1-scores of 0.96. The results indicate that ensemble and deep learning approaches can effectively support multiclass mental health risk classification. Because the provenance and label construction of the secondary dataset are not documented, the results should be read as within-dataset performance. The findings provide a basis for future real-world validation and decision-support applications.
SN  - 3069-1834
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Ahmad2026A,
  author = {Shoaib Ahmad and Ali Imran and Tahoona Kshif and Zubdah Tur Rasheed and Ayesha Khan and Aamir Ali and Muhammad Ali},
  title = {A Software-Oriented Deep Learning Framework for Multiclass Academic Stress and Mental Health Risk Prediction},
  journal = {ICCK Journal of Software Engineering},
  year = {2026},
  volume = {2},
  number = {3},
  pages = {220-247},
  doi = {10.62762/JSE.2026.690220},
  url = {https://www.icck.org/article/abs/JSE.2026.690220},
  abstract = {Student mental health and academic stress are significant concerns in higher education, creating a need for effective approaches to early risk identification. This study proposes a multiclass predictive framework for academic stress and mental health risk classification among students. The framework was developed using a Kaggle dataset containing 25,000 records with demographic, academic, behavioral, psychological, lifestyle, and medical attributes. A unified comparison was conducted across six conventional machine learning algorithms, namely Decision Tree, Random Forest, XGBoost, CatBoost, K-Nearest Neighbors (KNN), and Naïve Bayes, and three deep learning architectures, namely Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Bidirectional Long Short-Term Memory (BiLSTM). Class imbalance was addressed using the Synthetic Minority Over-sampling Technique (SMOTE), applied only to the training data, and model performance was evaluated using accuracy, precision, recall, F1-score, and confusion matrices. CatBoost and BiLSTM achieved the highest classification accuracy of 97\%, with weighted F1-scores of 0.97 and macro F1-scores of 0.96. The results indicate that ensemble and deep learning approaches can effectively support multiclass mental health risk classification. Because the provenance and label construction of the secondary dataset are not documented, the results should be read as within-dataset performance. The findings provide a basis for future real-world validation and decision-support applications.},
  keywords = {academic stress, mental health risk, deep learning, multiclass classification, BiLSTM, CatBoost, student well-being, SMOTE, predictive analytics},
  issn = {3069-1834},
  publisher = {Institute of Central Computation and Knowledge}
}