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

TL;DR

The results show that depression detection models do not generalize globally, and 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.

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.

Figures (2)

• Figure 1: Flow chart of the overall design of the work. This shows the training and evaluation process. n=datasets, m=models.
• Figure 2: The box plot illustrates the distribution of tokens across the datasets.