Behavioral Indicators of Loneliness: Predicting University Students' Loneliness Scores from Smartphone Sensing Data

TL;DR

This study demonstrates that passive smartphone sensing combined with machine learning can effectively predict university students' loneliness levels in real-time, offering scalable mental health monitoring tools.

Contribution

It introduces a novel approach integrating smartphone sensing with machine learning and large language models to predict loneliness dynamically and accurately.

Findings

Random Forest models achieved MAE of 3.29 and 3.98 on UCLA scale.

Large language models reduced prediction errors by up to 42%.

Key predictors include screen usage and location mobility.

Abstract

Loneliness is a critical mental health issue among university students, yet traditional monitoring methods rely primarily on retrospective self-reports and often lack real-time behavioral context. This study explores the use of passive smartphone sensing data to predict loneliness levels, addressing the limitations of existing approaches in capturing its dynamic nature. We integrate smartphone sensing with machine learning and large language models respectively to develop generalized and personalized models. Our Random Forest generalized models achieved mean absolute errors of 3.29 at midterm and 3.98 (out of 32) at the end of semester on the UCLA Loneliness Scale (short form), identifying smartphone screen usage and location mobility to be key predictors. The one-shot approach leveraging large language models reduced prediction errors by up to 42% compared to zero-shot inference. The one-shot results from personalized models highlighted screen usage, application usage, battery, and location transitions as salient behavioral indicators. These findings demonstrate the potential of smartphone sensing data for scalable and interpretable loneliness detection in digital mental health.