Chinese mental health dataset reveals social media language differences

MATCHA: A Chinese Multi-Disorder Mental Health Dataset with Cross-Lingual Analyses on Social Media

Computation and Language

Summary

Most studies about mental health on social media focus on English speakers and use a specific manual for diagnosing disorders, limiting understanding of other languages and cultures. The authors created MATCHA, a large dataset from Chinese social media that links users discussing seven different mental health disorders with their public posts. They used a smart method to identify users who clearly say they have these disorders and compared language and behavior across disorders and between Chinese and English social media platforms. Their work shows that language and expression vary more between platforms than between disorders, providing new data for mental health research in different languages.

What this means in practice

  • For social media analysis teams: Use the MATCHA dataset to develop better tools for detecting mental health signals in Chinese-language social media posts.
  • For mental health technology developers: Enhance cross-cultural mental health monitoring apps by incorporating bilingual data and insights from MATCHA to improve diagnosis sensitivity across languages.$Commercial implications: Enables creation of bilingual mental health tools for Chinese-speaking markets, extending beyond English-centered approaches.

Authors

Bingrui Jin, Baihan Li, Zitong Li, Kunyao Lan, Shimeng Li, Kenny Q. Zhu, Mengyue Wu

Abstract

Mental health research on social media has been dominated by English-language datasets and DSM-5-centered resources, limiting cross-lingual and cross-cultural understanding of online mental health expression. We introduce MATCHA, the first Chinese multi-disorder mental health dataset that links disorder-specific Weibo Super-Topic communities with users' broader public timelines. MATCHA covers seven DSM-5 disorders and a control group, comprising 46,025 cohort-level users and 1.8 million posts. The dataset distinguishes users with explicit self-disclosure evidence from broader disorder-related participants through an LLM-assisted annotation pipeline, and is released in a rigorously de-identified, controlled-access format. Using MATCHA, we analyze behavioral, linguistic, symptom-related, and life-event-related patterns across disorders, and conduct cross-lingual comparisons with Twitter-STMHD. Our analyses show that Weibo Super-Topics function as concentrated spaces for affective and health-related expression, while cross-platform differences between Weibo and Twitter often exceed cross-disorder variation. MATCHA provides a new resource for community-aware and cross-lingual mental health NLP research.
View PDFOpen arXiv