Manuscript received July 5, 2022; revised August 22, 2022; accepted January 11, 2023.
Abstract—More research is being done to find out how well-being can be predicted using well-designed models. To create a workable Subjective Well-Being (SWB) model, it is vital to look at the backgrounds of characteristics. From the SWB literature, we have chosen variables that are appropriate for real-world data instructions. The objective of this work is to assess the model's performance on a real dataset by giving it SWB determinants and then classifying stress levels using machine learning techniques. Although it is a multiclass classification problem, we have nevertheless managed to obtain meaningful metric scores that can be considered for a particular assignment.
Index Terms—Machine learning, multiclassification, subjective well-being, perceived stress scale
A. Karakuş is with the Galatasaray University, Logistics and Financial Management, 34349, Istanbul, Turkye.
A. C. Kılıç is with İstanbul Kültür University, Department of Industrial Engineering, 34158, Istanbul, Turkye.
S. E. Alptekin is with the Galatasaray University, 34349, Istanbul, Turkye.
Cite: Ahmet Karakuş, Akif Can Kılıç, and S. Emre Alptekin, "Prediction of Mental Health: Heuristic Subjective Well-Being Model on Perceived Stress Scale Using Machine Learning Algorithms," International Journal of Machine Learning vol. 13, no. 3, pp. 117-124, 2023.
Copyright @ 2023 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).