Using Open-Ended Stressor Responses to Predict Depressive Symptoms across Demographics

TL;DR

This study explores how open-ended stressor responses relate to depressive symptoms across different demographics, using NLP to identify themes and predict depression, revealing demographic differences in stressors and model performance.

Contribution

It introduces a novel approach combining NLP and language models to analyze open-ended stressor responses and predict depression across diverse demographic groups.

Findings

Stressors vary in themes and vocabulary across demographics.

Language models can predict depressive symptoms from stressor responses.

Performance of depression prediction models differs across demographic groups.

Abstract

Stressors are related to depression, but this relationship is complex. We investigate the relationship between open-ended text responses about stressors and depressive symptoms across gender and racial/ethnic groups. First, we use topic models and other NLP tools to find thematic and vocabulary differences when reporting stressors across demographic groups. We train language models using self-reported stressors to predict depressive symptoms, finding a relationship between stressors and depression. Finally, we find that differences in stressors translate to downstream performance differences across demographic groups.