7 November 2019 in Proceedings of the ACM on Human-Computer Interaction
A deep understanding of how discrimination impacts psychological health and well-being of students could allow us to better protect individuals at risk and support those who encounter discrimination. While the link between discrimination and diminished psychological and physical well-being is well established, existing research largely focuses on chronic discrimination and long-term outcomes. A better understanding of the short-term behavioral correlates of discrimination events could help us to concretely quantify such experiences, which in turn could support policy and intervention design. In this paper we specifically examine, for the first time, what behaviors change and in what ways in relation to discrimination. We use actively-reported and passively-measured markers of health and well-being in a sample of 209 first-year college students over the course of two academic quarters. We examine changes in indicators of psychological state in relation to reports of unfair treatment in terms of five categories of behaviors: physical activity, phone usage, social interaction, mobility, and sleep. We find that students who encounter unfair treatment become more physically active, interact more with their phone in the morning, make more calls in the evening, and spend more time in bed on the day of the event. Some of these patterns continue the next day. Our results further our understanding of the impact of discrimination and can inform intervention work.
21 December 2022 in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
There is a growing body of research revealing that longitudinal passive sensing data from smartphones and wearable devices can capture daily behavior signals for human behavior modeling, such as depression detection. Most prior studies build and evaluate machine learning models using data collected from a single population. However, to ensure that a behavior model can work for a larger group of users, its generalizability needs to be verified on multiple datasets from different populations. We present the first work evaluating cross-dataset generalizability of longitudinal behavior models, using depression detection as an application. We collect multiple longitudinal passive mobile sensing datasets with over 500 users from two institutes over a two-year span, leading to four institute-year datasets. Using the datasets, we closely re-implement and evaluated nine prior depression detection algorithms. Our experiment reveals the lack of model generalizability of these methods. We also implement eight recently popular domain generalization algorithms from the machine learning community. Our results indicate that these methods also do not generalize well on our datasets, with barely any advantage over the naive baseline of guessing the majority. We then present two new algorithms with better generalizability. Our new algorithm, Reorder, significantly and consistently outperforms existing methods on most cross-dataset generalization setups. However, the overall advantage is incremental and still has great room for improvement. Our analysis reveals that the individual differences (both within and between populations) may play the most important role in the cross-dataset generalization challenge. Finally, we provide an open-source benchmark platform GLOBEM- short for Generalization of Longitudinal BEhavior Modeling - to consolidate all 19 algorithms. GLOBEM can support researchers in using, developing, and evaluating different longitudinal behavior modeling methods. We call for researchers' attention to model generalizability evaluation for future longitudinal human behavior modeling studies.
28 April 2022 in Nature Human Behaviour
24 April 2015 in Suicide and Life-Threatening Behavior
1 March 2015 in Journal of Child and Adolescent Psychopharmacology
The present study investigates the longitudinal relationship between perceived family and peer invalidation and adolescent suicidal events (SE) and self-mutilation (SM) in a 6 month follow-up (f/u) study of adolescents admitted to an inpatient psychiatric unit for suicide risk. Adolescents (n=119) and their parent(s) were administered interviews and self-report assessments at baseline and at a 6 month f/u, with 99 (83%) completing both assessments. The Adolescent Longitudinal Interval Follow-Up Evaluation (A-LIFE) was modified to provide weekly ratings (baseline and each week of f/u) for perceived family and peer invalidation. Regression analyses examined whether: 1) Prospectively rated perceived family and peer invalidation at baseline predicted SE and SM during f/u; and 2) chronicity of perceived invalidation operationalized as proportion of weeks at moderate to high invalidation during f/u was associated with SE and SM during f/u. Multiple regression analyses, controlling for previously identified covariates, revealed that perceived family invalidation predicted SE over f/u for boys only and perceived peer invalidation predicted SM over f/u in the overall sample. This was the case for both baseline and f/u ratings of perceived invalidation. Our results demonstrate the adverse impact of perceived family and peer invalidation. Specifically, boys who experienced high perceived family invalidation were more likely to have an SE over f/u. Both boys and girls who experienced high perceived peer invalidation were more likely to engage in SM over f/u.
31 May 2024 in Journal of Affective Disorders