arXiv subjects

Caroline Figueroa

Publications and source records attributed to Caroline Figueroa.

4 recordsLinked to original sources

arXiv2026

Reading Between the Signs: Predicting Future Suicidal Ideation from Adolescent Social Media Texts

Suicide is a leading cause of death, yet predicting it remains a significant challenge. Risk factors such as depression or substance use are commonly used for prediction, but their predictive performance is often only slightly better than chance. Additionally, many cases go undetected due to a lack of contact with mental health services. Social media, however, offers a unique opportunity, as people often share their thoughts and struggles online in real time. In this work, we propose a novel task and method for early identification: predicting suicidal ideation and behavior (SIB) before a user ever expresses it on an online forum. We introduce Early-SIB, a transformer-based model that sequentially processes the posts a user writes and engages with to predict whether they will write a SIB post. Our model achieves a balanced accuracy of 0.73 in predicting future SIB on a Dutch youth forum, demonstrating that such tools can offer a meaningful addition to traditional methods. Finally, we use Shapley Additive Explanations to make the model's predictions more interpretable.

cs.CL↗

arXiv2025

Signs of Struggle: Spotting Cognitive Distortions across Language and Register

Rising mental health issues among youth have increased interest in automated approaches for detecting early signs of psychological distress in digital text. One key focus is the identification of cognitive distortions, irrational thought patterns that have a role in aggravating mental distress. Early detection of these distortions may enable timely, low-cost interventions. While prior work has focused on English clinical data, we present the first in-depth study of cross-lingual and cross-register generalization of cognitive distortion detection, analyzing forum posts written by Dutch adolescents. Our findings show that while changes in language and writing style can significantly affect model performance, domain adaptation methods show the most promise.

cs.CL↗

arXiv2023

A Flexible Micro-Randomized Trial Design and Sample Size Considerations

Technological advancements have made it possible to deliver mobile health interventions to individuals. A novel framework that has emerged from such advancements is the just-in-time adaptive intervention (JITAI), which aims to suggest the right support to the individuals when their needs arise. The micro-randomized trial (MRT) design has been proposed recently to test the proximal effects of these JITAIs. However, the extant MRT framework only considers components with a fixed number of categories added at the beginning of the study. We propose a flexible MRT (FlexiMRT) design which allows addition of more categories to the components during the study. The proposed design is motivated by collaboration on the DIAMANTE study, which learns to deliver text messages to encourage physical activity among the patients with diabetes and depression. We developed a new test statistic and the corresponding sample size calculator for the FlexiMRT using an approach similar to the generalized estimating equation for longitudinal data. Simulation studies were conducted to evaluate the sample size calculators and an R shiny application for the calculators was developed.

stat.ME↗

arXiv2020

Multi-Level Micro-Randomized Trial: Detecting the Proximal Effect of Messages on Physical Activity

Technological advancements in mobile devices have made it possible to deliver mobile health interventions to individuals. A novel intervention framework that emerges from such advancements is the just-in-time adaptive intervention (JITAI), where it aims to suggest the right support to the individual "just in time", when their needs arise, thus having proximal, near future effects. The micro-randomized trial (MRT) design was proposed recently to test the proximal effects of these JITAIs. In an MRT, participants are repeatedly randomized to one of the intervention options of various in the intervention components, at a scale of hundreds or thousands of decision time points over the course of the study. However, the extant MRT framework only tests the proximal effect of two-level intervention components (e.g. control vs intervention). In this paper, we propose a novel version of MRT design with multiple levels per intervention component, which we call "multi-level micro-randomized trial" (MLMRT) design. The MLMRT extends the existing MRT design by allowing multi-level intervention components, and the addition of more levels to the components during the study period. We apply generalized estimating equation type methodology on the longitudinal data arising from an MLMRT to develop the novel test statistics for assessing the proximal effects and deriving the associated sample size calculators. We conduct simulation studies to evaluate the sample size calculators based on both power and precision. We have developed an R shiny application of the sample size calculators. This proposed design is motivated by our involvement in the Diabetes and Mental Health Adaptive Notification Tracking and Evaluation (DIAMANTE) study. This study uses a novel mobile application, also called "DIAMANTE", which delivers adaptive text messages to encourage physical activity.

stat.ME↗