JMIR Publications

ABSTRACT

Background:

Experiences of unfair treatment on college campuses are linked to adverse mental and physical health outcomes, highlighting the need for interventions. However, detecting such experiences relies mainly on self-reports. No prior research has examined the feasibility of using mobile sensing via smartphones and wearables for the passive detection of these experiences.

Objective:

This pilot study explores the potential of using passive sensing to infer daily experiences of perceived unfair treatment. It aims to develop and evaluate machine learning models against naive baselines and establish a benchmark for future research.

Methods:

We analyzed data from 201 undergraduate students collected over two 10-week academic terms in 2018. Perceived unfair treatment was self-reported at the daily level via ecological momentary assessment (EMA) surveys, with 413 of 9629 total responses (< 5%) indicating unfair treatment. We implemented two modeling approaches with distinct training schemes: (a) supervised classification models trained in a user-independent manner using data from different individuals, and (b) anomaly detection models trained in a user-dependent manner using historical data from the same individuals. Classification performance was assessed using stratified group 5-fold cross-validation for user-independent models and a chronological train-test split for user-dependent models.

Results:

Of the 201 study participants, 110 reported experiencing unfair treatment at least once. On average, participants reported unfair treatment in 4.66% of their EMA responses (95% CI: 3.13% to 6.19%). User-independent classification models showed mixed performance, with AUC values ranging from 0.57 to 0.67 and F1 scores between 0.07 and 0.16. Among them, LightGBM performed best and outperformed the demographic baseline. In contrast, user-dependent anomaly detection models performed better, with the multi-day LSTM-AE model achieving the highest performance (precision: 0.27, recall: 0.84, F1: 0.41), outperforming naive baselines. Feature importance analysis identified key behavioral patterns for population-level detection, including increased time spent off campus, elevated evening and nighttime activity, reduced indoor mobility on campus, prolonged screen usage, delayed sleep onset, and shorter sleep duration.

Conclusions:

Mobile sensing shows promise for detecting daily experiences of perceived unfair treatment in college students and identifying associated behavioral patterns. Our findings highlight opportunities for timely interventions through mobile technology to mitigate the impact of these experiences on students’ mental health and well-being.