Using Open-Ended Stressor Responses to Predict Depressive Symptoms across Demographics
This addresses mental health assessment disparities across demographic groups, though it is incremental in applying existing NLP methods to this specific problem.
The study investigated how open-ended text responses about stressors predict depressive symptoms across different demographic groups, finding that differences in how stressors are reported lead to performance disparities in predicting depression across groups.
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.