A Survey on Multilingual Mental Disorders Detection from Social Media Data

2025-05-21

AI Summary

Existing mental health disorder detection research heavily relies on English-language data, overlooking culture-specific linguistic patterns and self-disclosure behaviors in non-English contexts, thereby limiting cross-lingual screening efficacy. This paper presents the first systematic review of mental disorder detection in multilingual social media, integrating natural language processing, cross-lingual transfer learning, cultural linguistics, and social computing approaches to uncover how cultural factors mechanistically influence NLP model performance. Key contributions include: (1) a comprehensive, first-of-its-kind landscape mapping of multilingual mental health detection studies; (2) principled guidelines for designing culturally adaptive screening frameworks; (3) identification of 12 critical sources of language–culture bias; and (4) a curated, open-source inventory of 83 reusable mental health datasets spanning 47 languages—addressing a critical gap in cross-lingual digital mental health screening.

Technology Category

• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP
• Machine Learning: Multimodal Learning
• Application Domains: Humanities & Computational Social Science

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Social Networks and Social Media: Fairness and bias in social network and social media analysis

Abstract

The increasing prevalence of mental health disorders globally highlights the urgent need for effective digital screening methods that can be used in multilingual contexts. Most existing studies, however, focus on English data, overlooking critical mental health signals that may be present in non-English texts. To address this important gap, we present the first survey on the detection of mental health disorders using multilingual social media data. We investigate the cultural nuances that influence online language patterns and self-disclosure behaviors, and how these factors can impact the performance of NLP tools. Additionally, we provide a comprehensive list of multilingual data collections that can be used for developing NLP models for mental health screening. Our findings can inform the design of effective multilingual mental health screening tools that can meet the needs of diverse populations, ultimately improving mental health outcomes on a global scale.

Problem

• Detecting mental disorders from multilingual social media data
• Addressing cultural nuances in online language for NLP tools
• Providing multilingual datasets for mental health screening models

Innovation

• Survey on multilingual mental disorder detection
• Analyze cultural nuances in online language patterns
• Provide multilingual data collections for NLP models