Risk and protective factors of psychological pain using machine learning
Acta Psychologica · 2026-10 · 270 · 107812
DOI: 10.1016/j.actpsy.2026.107812 ↗Kurz gefasst
Fachartikel in der Zeitschrift Acta Psychologica, 2026-10. Verfasst von Murat Yıldırım und 4 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Science and Letters, Department of Psychology, Agri Ibrahim Cecen University, Ağrı, Türkiye; Psychology Research Center, Khazar University…. Hauptthemen laut MEDLINE: Machine Learning, Stress, Psychological, Pessimism, Psychological Distress. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Psychological pain is of vital importance due to its link to suicidality. The present study sought to examine the psychometric properties of A Brief Measure of Unbearable Psychache, to investigate the roles of psychological distress, pessimism, meaning in life, hope, and demographic variables (age, gender, perceived economic status, marital status, and education level) in predicting psychological pain, to construct an optimal prediction model using a machine learning approach, to rank the feature importance of the possible predictors of psychological pain and to explain the contributions and direction of influence of the variables. This study included 432 participants (76.9% females), and the mean age of the participants was 24.26 years (SD = 6.47). The study findings determined that the psychometric properties of A Brief Measure of Unbearable Psychache had sufficient validity and reliability in Turkish culture. The results of the current study showed that the two most critical factors predicting psychological pain were psychological distress and pessimism, respectively. Hope and meaning in life were the other psychological variables. While psychological stress and pessimism had a positive effect, hope and meaning in life had a negative effect on psychological pain. The contribution of demographic factors was quite limited. These results highlight the relative superiority of psychological factors over demographic characteristics in predicting psychological pain. This study suggests the development of preventive and intervention programs aimed at reducing risk factors and strengthening protective factors for psychache sufferers or those at risk.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Science and Letters, Department of Psychology, Agri Ibrahim Cecen University, Ağrı, Türkiye; Psychology Research Center, Khazar University, Baku, Azerbaijan. Electronic address: muratyildirim@agri.edu.tr.
- Department of Psychology, Faculty of Science and Letters, Agri Ibrahim Cecen University, Ağrı, Türkiye. Electronic address: ggoztekin@agri.edu.tr.
- Department of Computer Engineering, Agri Ibrahim Cecen University, Ağrı, Türkiye. Electronic address: ebasaran@agri.edu.tr.
- Inonu University, Faculty of Science and Letters, Department of Psychology, Malatya, Türkiye. Electronic address: zaferguney.cagis@inonu.edu.tr.
- Department of Medicine and Public Health, Faculty of Labour Sciences, University of Huelva, 21071, Huelva, Spain; Safety and Health Postgraduate Program, Universidad Espíritu Santo, Guayaquil, 092301, Ecuador. Electroni…
Zitieren
APA
Yıldırım, M., Öztekin, G. G., Başaran, E., Çağış, Z. G., & Gómez-Salgado, J. (2026). Risk and protective factors of psychological pain using machine learning. Acta Psychologica, 270, 107812. https://doi.org/10.1016/j.actpsy.2026.107812
Vancouver
Yıldırım M, Öztekin GG, Başaran E, Çağış ZG, Gómez-Salgado J. Risk and protective factors of psychological pain using machine learning. Acta Psychologica. 2026;270:107812. doi:10.1016/j.actpsy.2026.107812
BibTeX
@article{Yldrm2026,
author = {Yıldırım, Murat and Öztekin, Gülçin Güler and Başaran, Erdal and Çağış, Zafer Güney and Gómez-Salgado, Juan},
title = {Risk and protective factors of psychological pain using machine learning},
journal = {Acta Psychologica},
year = {2026},
volume = {270},
pages = {107812},
doi = {10.1016/j.actpsy.2026.107812}
}
EUVIMED