Unmasking the Nuances of Loneliness: Using Digital Biomarkers to Understand Social and Emotional Loneliness in College Students

TL;DR

The paper tackles the problem of distinguishing social and emotional loneliness in college students by leveraging digital biomarkers derived from passive sensing. It combines descriptive statistics, nonparametric experiments, and machine learning (notably XGBoost with SHAP) to classify loneliness into four categories, achieving up to 78.5% accuracy. Key findings show distinct behavioural signatures, such as differences in phone usage and mobility, that differentiate loneliness types, enabling more personalized interventions. The study demonstrates the practical potential of passive sensing for early detection and targeted support, while also outlining limitations and directions for broader, mixed-methods research.

Abstract

Background: Loneliness among students is increasing across the world, with potential consequences for mental health and academic success. To address this growing problem, accurate methods of detection are needed to identify loneliness and to differentiate social and emotional loneliness so that intervention can be personalized to individual need. Passive sensing technology provides a unique technique to capture behavioral patterns linked with distinct loneliness forms, allowing for more nuanced understanding and interventions for loneliness. Methods: To differentiate between social and emotional loneliness using digital biomarkers, our study included statistical tests, machine learning for predictive modeling, and SHAP values for feature importance analysis, revealing important factors in loneliness classification. Results: Our analysis revealed significant behavioral differences between socially and emotionally lonely groups, particularly in terms of phone usage and location-based features , with machine learning models demonstrating substantial predictive power in classifying loneliness levels. The XGBoost model, in particular, showed high accuracy and was effective in identifying key digital biomarkers, including phone usage duration and location-based features, as significant predictors of loneliness categories. Conclusion: This study underscores the potential of passive sensing data, combined with machine learning techniques, to provide insights into the behavioral manifestations of social and emotional loneliness among students. The identification of key digital biomarkers paves the way for targeted interventions aimed at mitigating loneliness in this population.

Figures (4)

• Figure 1: Mean Difference and Effect Sizes of biomarkers between socially and emotionally lonely groups
• Figure 2: Performance of classification models for loneliness prediction. The model performances are compared with three baseline classifiers (BL1:MC = BaseLine 1 Majority Class; BL2:DT = BaseLine 2 Decision Tree, and BL3:RWC = BaseLine 3 Random Weighted Classifier; SVM = Support Vector Machine, RF = Random Forest, KNN = K-Nearest Neighbors). All values are reported as percentages.
• Figure 3: Mean Feature Importance using SHAP for XGBoost model
• Figure 4: Mean Feature Importance using SHAP for Random Forest model