@inproceedings{56c6324b911d4365842efa32e7a4dbdf,
title = "Qualitative Analysis of Depression Models by Demographics",
abstract = "Models for identifying depression using social media text exhibit biases towards different gender and racial/ethnic groups. Factors like representation and balance of groups within the dataset are contributory factors, but difference in content and social media use may further explain these biases. We present an analysis of the content of social media posts from different demographic groups. Our analysis shows that there are content differences between depression and control subgroups across demographic groups, and that temporal topics and demographic-specific topics are correlated with downstream depression model error. We discuss the implications of our work on creating future datasets, as well as designing and training models for mental health.",
author = "Carlos Aguirre and Mark Dredze",
note = "Publisher Copyright: {\textcopyright}2021 Association for Computational Linguistics.; 7th Workshop on Computational Linguistics and Clinical Psychology: Improving Access, CLPsych 2021 ; Conference date: 11-06-2021",
year = "2021",
language = "English (US)",
series = "Computational Linguistics and Clinical Psychology: Improving Access, CLPsych 2021 - Proceedings of the 7th Workshop, in conjunction with NAACL 2021",
publisher = "Association for Computational Linguistics (ACL)",
pages = "169--180",
editor = "Nazli Goharian and Philip Resnik and Andrew Yates and Molly Ireland and Kate Niederhoffer and Rebecca Resnik",
booktitle = "Computational Linguistics and Clinical Psychology",
address = "United States",
}