Unlocking Mental Health: Exploring College Students' Well-being through Smartphone Behaviors

TL;DR

This paper addresses how real-world smartphone unlocking behaviors relate to college students' mental health, using four years of longitudinal mobile sensing from the College Experience Study (CES) dataset. It investigates unlocking frequency and duration as predictive features for PHQ4 categories via Pearson correlations and multinomial logistic regression, with analyses stratified by gender and location. Key contributions include the first large-scale, real-world analysis of unlocking behaviors across iOS and Android, evidence that unlocking features can predict mental health status, and clear gender- and context-dependent differences that inform personalized predictive models and interventions. The work highlights that longer unlock durations tend to associate with poorer mental health while higher unlock frequency can relate to better outcomes, and it proposes context-aware, lightweight predictive approaches with open-source pipelines to advance digital well-being research in college populations.

Abstract

The global mental health crisis is a pressing concern, with college students particularly vulnerable to rising mental health disorders. The widespread use of smartphones among young adults, while offering numerous benefits, has also been linked to negative outcomes such as addiction and regret, significantly impacting well-being. Leveraging the longest longitudinal dataset collected over four college years through passive mobile sensing, this study is the first to examine the relationship between students' smartphone unlocking behaviors and their mental health at scale in real-world settings. We provide the first evidence demonstrating the predictability of phone unlocking behaviors for mental health outcomes based on a large dataset, highlighting the potential of these novel features for future predictive models. Our findings reveal important variations in smartphone usage across genders and locations, offering a deeper understanding of the interplay between digital behaviors and mental health. We highlight future research directions aimed at mitigating adverse effects and promoting digital well-being in this population.

Figures (2)

• Figure 1: Distributions of Unlock Number, Unlock Duration, and Duration per Unlock at the individual level with mean values (top) and maximum values (bottom). Excluded data points described in Section \ref{['data']} are shown in red.
• Figure 2: Gender differences highlighted based on the same data shown in Fig. \ref{['fig1']}