EUVIMEDEUVIMED entdecken
Crossref

Data Analytics and Machine Learning Approaches for Predicting Academic Stress and Enhancing Student Wellbeing

International Journal of Advance Research and Innovation · 31.12.2025 · 13 (4) · 23-29

DOI: 10.69996/ijari.2025021 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Advance Research and Innovation, online erschienen am 31.12.2025. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Academic stress has emerged as a significant factor affecting student performance, mental health, and overall well-being. This study proposes a Blockchain-enabled Data Analytics and Machine Learning (B-DAML) framework for predicting academic stress and facilitating timely interventions to enhance student well-being. The framework integrates multimodal data, including academic records, behavioral patterns, and psychological assessments, securely stored on a blockchain to ensure data integrity and privacy. Multiple machine learning models—Logistic Regression, Support Vector Machine, Random Forest, Gradient Boosting (XGBoost), and Neural Networks—were trained and evaluated on a dataset of 500 students. Simulation results demonstrate that XGBoost achieves the highest predictive performance with 88.3% accuracy and an F1-score of 0.88, effectively identifying students at high risk of stress. Feature analysis indicates that stress survey scores, sleep duration, and study patterns are the most significant predictors. The framework also maps predicted stress levels to actionable interventions, including personalized study plans, mindfulness sessions, and counseling, demonstrating potential stress reduction of up to 30% in high-risk students. By combining secure data management, predictive analytics, and targeted interventions, the proposed approach offers a scalable, practical solution for educational institutions to monitor, predict, and mitigate academic stress, fostering improved student well-being and academic outcomes.

Zitieren

APA

(2025). Data Analytics and Machine Learning Approaches for Predicting Academic Stress and Enhancing Student Wellbeing. International Journal of Advance Research and Innovation, 13(4), 23-29. https://doi.org/10.69996/ijari.2025021

Vancouver

Data Analytics and Machine Learning Approaches for Predicting Academic Stress and Enhancing Student Wellbeing. International Journal of Advance Research and Innovation. 2025;13(4):23-29. doi:10.69996/ijari.2025021

BibTeX
@article{euvimed2025,
  title = {Data Analytics and Machine Learning Approaches for Predicting Academic Stress and Enhancing Student Wellbeing},
  journal = {International Journal of Advance Research and Innovation},
  year = {2025},
  volume = {13},
  number = {4},
  pages = {23--29},
  doi = {10.69996/ijari.2025021}
}
Kostenlos starten →