Diverse Perspectives, Divergent Models: Cross-Cultural Evaluation of Depression Detection on Twitter

TL;DR

This study evaluates how well depression detection models trained on Twitter data generalize across different cultures, revealing significant performance gaps especially for Global South users and emphasizing the need for culturally diverse datasets.

Contribution

It introduces a cross-cultural Twitter dataset for depression detection and systematically assesses the models' generalization across diverse cultural groups.

Findings

Models perform worse on Global South users

Pre-trained language models outperform logistic regression

Significant performance gaps remain for non-Western users

Abstract

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.