Predicting life satisfaction using machine learning and explainable AI

2025-10-18

AI Summary

Traditional life satisfaction assessments suffer from subjectivity, methodological complexity, and poor reproducibility. Method: Leveraging survey data from 19,000 Danish respondents, we developed an interpretable machine learning (XAI) framework—shifting life satisfaction prediction from clinical to biomedical paradigms for the first time. We derived a 27-item parsimonious scale and transformed structured survey features into natural language inputs via feature learning, resampling, and selection, enabling clinical/biomedical large language models (LLMs) to perform prediction. Contribution/Results: Our XAI model achieves 93.80% accuracy and a macro F1-score of 73.00%; LLM-based prediction attains comparable performance (93.74% accuracy, 73.21% macro F1), validating feasibility. Crucially, health status emerges as the strongest cross-age predictor. This work establishes a high-accuracy, interpretable, and generalizable paradigm for quantifying subjective well-being.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Life satisfaction is a crucial facet of human well-being. Hence, research on life satisfaction is incumbent for understanding how individuals experience their lives and influencing interventions targeted at enhancing mental health and well-being. Life satisfaction has traditionally been measured using analog, complicated, and frequently error-prone methods. These methods raise questions concerning validation and propagation. However, this study demonstrates the potential for machine learning algorithms to predict life satisfaction with a high accuracy of 93.80% and a 73.00% macro F1-score. The dataset comes from a government survey of 19000 people aged 16-64 years in Denmark. Using feature learning techniques, 27 significant questions for assessing contentment were extracted, making the study highly reproducible, simple, and easily interpretable. Furthermore, clinical and biomedical large language models (LLMs) were explored for predicting life satisfaction by converting tabular data into natural language sentences through mapping and adding meaningful counterparts, achieving an accuracy of 93.74% and macro F1-score of 73.21%. It was found that life satisfaction prediction is more closely related to the biomedical domain than the clinical domain. Ablation studies were also conducted to understand the impact of data resampling and feature selection techniques on model performance. Moreover, the correlation between primary determinants with different age brackets was analyzed, and it was found that health condition is the most important determinant across all ages. This study demonstrates how machine learning, large language models and XAI can jointly contribute to building trust and understanding in using AI to investigate human behavior, with significant ramifications for academics and professionals working to quantify and comprehend subjective well-being.

Problem

• Predicting life satisfaction using machine learning with high accuracy
• Identifying key determinants of life satisfaction across different age groups
• Applying explainable AI to understand subjective well-being measurements

Innovation

• Machine learning predicts life satisfaction with high accuracy
• Feature learning extracts key questions for reproducible assessment
• LLMs convert tabular data to text for biomedical prediction