@article{20.500.12766/785,
year = {2024},
month = {12},
url = {https://hdl.handle.net/20.500.12766/785},
abstract = {In contemporary psychological assessments, diverse traits are often evaluated using extensive questionnaires. This study focuses on the trait of emotional stability, and acknowledges the inherent limitations and issues associated with prolonged survey instruments. To address these challenges, we propose a Machine Learning (ML) approach to directly predict emotional stability, offering a more efficient alternative to bulky questionnaires. The study carefully selected variables with previously established relationships to emotional stability, utilizing a dataset of 2203 individuals who responded to a series of psychometric questionnaires. The proposed method yields promising results, achieving an R2 score of approximately 0.71 on the test set, indicating robust predictive performance. These models highlighted the significance of variables such as emotional stress and self-esteem, emphasizing their substantial role in predicting emotional stability. It is noteworthy that even with a reduced set of variables, the models remained statistically equivalent. The results provide valuable insights for predicting stability with smaller sets of variables and contribute knowledge that complements the understanding of emotional stability.},
publisher = {Springer Nature},
title = {Exploring emotional stability: from conventional approaches to machine learning insights},
doi = {10.1007/s10489-024-06130-5},
journal = {Applied Intelligence},
keywords = {Machine learning},
keywords = {Data mining},
keywords = {Emotional stability},
keywords = {Psychology},
volume = {55},
author = {Romero Madroñal, Marcos and Ramírez Riveros, Eduar and Gonzaga Baca Ruiz, Luis and Serrano-Fernández, María José and Pérez-Moreiras, Elena and Pegalajar Jiménez, María del Carmen},
}