Predicting Life Satisfaction Using Artificial Neural Networks Based on Gratitude, Meaning in Life, Self-Compassion, and Resilience
Journal of Assessment and Research in Applied Counseling · 2026 · 8 (3) · 1-14
DOI: 10.61838/kman.jarac.5805 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Assessment and Research in Applied Counseling, 2026. Verfasst von Christian Hauser und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Objective
This study aimed to develop and evaluate an artificial neural network model for predicting life satisfaction among adults in Germany based on gratitude, meaning in life, self-compassion, and resilience. Methods and Materials: This cross-sectional predictive study was conducted on 1,162 adults in Germany. Data were collected using standardized self-report instruments, including the Satisfaction with Life Scale, Gratitude Questionnaire–Six Item Form, Meaning in Life Questionnaire, Self-Compassion Scale–Short Form, and Connor–Davidson Resilience Scale. After data screening, descriptive statistics, reliability analysis, Pearson correlations, and artificial neural network modeling were performed. The dataset was divided into training, validation, and testing subsets. A multilayer feedforward neural network was developed using standardized predictor variables, with model optimization performed through the Adam algorithm, early stopping, and dropout regularization. Model performance was evaluated using MAE, MSE, RMSE, R², explained variance, permutation feature importance, and SHAP analysis.
Findings
Pearson correlation analysis showed that all predictor variables had significant positive associations with life satisfaction. Resilience had the strongest correlation with life satisfaction, followed by self-compassion, meaning in life, and gratitude. The artificial neural network demonstrated strong predictive accuracy, explaining 86.5% of the variance in life satisfaction in the training set, 84.9% in the validation set, and 84.2% in the testing set. Prediction errors remained low across all datasets, indicating stable model performance and limited overfitting. Feature-importance analyses showed that resilience was the most influential predictor of life satisfaction, followed by self-compassion, meaning in life, and gratitude.
Conclusion
The findings indicate that life satisfaction can be predicted with high accuracy using an artificial neural network model based on positive psychological resources. Resilience, self-compassion, meaning in life, and gratitude jointly provide a strong predictive framework for understanding subjective well-being.
Zitieren
APA
Hauser, C., Lener, G., & Walg, Y. (2026). Predicting Life Satisfaction Using Artificial Neural Networks Based on Gratitude, Meaning in Life, Self-Compassion, and Resilience. Journal of Assessment and Research in Applied Counseling, 8(3), 1-14. https://doi.org/10.61838/kman.jarac.5805
Vancouver
Hauser C, Lener G, Walg Y. Predicting Life Satisfaction Using Artificial Neural Networks Based on Gratitude, Meaning in Life, Self-Compassion, and Resilience. Journal of Assessment and Research in Applied Counseling. 2026;8(3):1-14. doi:10.61838/kman.jarac.5805
BibTeX
@article{Hauser2026,
author = {Hauser, Christian and Lener, Gerhard and Walg, Yarden},
title = {Predicting Life Satisfaction Using Artificial Neural Networks Based on Gratitude, Meaning in Life, Self-Compassion, and Resilience},
journal = {Journal of Assessment and Research in Applied Counseling},
year = {2026},
volume = {8},
number = {3},
pages = {1--14},
doi = {10.61838/kman.jarac.5805}
}
EUVIMED