Saved in:
Bibliographic Details
Main Authors: Ali, Nuredin, Zhang, Charles Chuankai, Mayo, Ned, Chancellor, Stevie
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.15362
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916439540105216
author Ali, Nuredin
Zhang, Charles Chuankai
Mayo, Ned
Chancellor, Stevie
author_facet Ali, Nuredin
Zhang, Charles Chuankai
Mayo, Ned
Chancellor, Stevie
contents Social media data has been used for detecting users with mental disorders, such as depression. Despite the global significance of cross-cultural representation and its potential impact on model performance, publicly available datasets often lack crucial metadata related to this aspect. In this work, we evaluate the generalization of benchmark datasets to build AI models on cross-cultural Twitter data. We gather a custom geo-located Twitter dataset of depressed users from seven countries as a test dataset. Our results show that depression detection models do not generalize globally. The models perform worse on Global South users compared to Global North. Pre-trained language models achieve the best generalization compared to Logistic Regression, though still show significant gaps in performance on depressed and non-Western users. We quantify our findings and provide several actionable suggestions to mitigate this issue.
format Preprint
id arxiv_https___arxiv_org_abs_2406_15362
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Diverse Perspectives, Divergent Models: Cross-Cultural Evaluation of Depression Detection on Twitter
Ali, Nuredin
Zhang, Charles Chuankai
Mayo, Ned
Chancellor, Stevie
Computation and Language
Social media data has been used for detecting users with mental disorders, such as depression. Despite the global significance of cross-cultural representation and its potential impact on model performance, publicly available datasets often lack crucial metadata related to this aspect. In this work, we evaluate the generalization of benchmark datasets to build AI models on cross-cultural Twitter data. We gather a custom geo-located Twitter dataset of depressed users from seven countries as a test dataset. Our results show that depression detection models do not generalize globally. The models perform worse on Global South users compared to Global North. Pre-trained language models achieve the best generalization compared to Logistic Regression, though still show significant gaps in performance on depressed and non-Western users. We quantify our findings and provide several actionable suggestions to mitigate this issue.
title Diverse Perspectives, Divergent Models: Cross-Cultural Evaluation of Depression Detection on Twitter
topic Computation and Language
url https://arxiv.org/abs/2406.15362