Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Survey on Multilingual Mental Disorders Detection from Social Media Data

Ana-Maria Bucur, Marcos Zampieri, Tharindu Ranasinghe, Fabio Crestani

TL;DR

This survey addresses the gap in multilingual mental health detection from social media, highlighting cross-cultural and cross-language differences in online expression. It catalogs multilingual datasets, tasks, and methodological approaches, enabling researchers to leverage non-English resources. The paper reviews classical, transformer-based, translation, and multilingual strategies and documents ethical and practical considerations. By identifying data scarcity and annotation/explainability gaps, it calls for coordinated, culturally aware, multilingual efforts to improve global mental health screening.

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.

A Survey on Multilingual Mental Disorders Detection from Social Media Data

TL;DR

This survey addresses the gap in multilingual mental health detection from social media, highlighting cross-cultural and cross-language differences in online expression. It catalogs multilingual datasets, tasks, and methodological approaches, enabling researchers to leverage non-English resources. The paper reviews classical, transformer-based, translation, and multilingual strategies and documents ethical and practical considerations. By identifying data scarcity and annotation/explainability gaps, it calls for coordinated, culturally aware, multilingual efforts to improve global mental health screening.

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.

Paper Structure

This paper contains 37 sections, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Surveys
  3. Mental Disorders Detection Tasks Overview
  4. Shared Tasks
  5. Methodology
  6. Multilingual Datasets
  7. Data Sources
  8. Languages
  9. Mental Disorders
  10. Annotation Procedure
  11. Availability of Data Collections
  12. Mental Disorders Detection Approaches
  13. Classical approaches
  14. Pre-trained transformer-based models
  15. Translation
  16. ...and 22 more sections

Figures (4)

  • Figure 1: Overview of tasks related to detecting mental health problems from social media.
  • Figure 2: Overview of the mental disorders addressed in each dataset, along with the annotation procedures.
  • Figure 3: PRISMA flow diagram for our review.
  • Figure 4: Overview of the languages in the datasets, their language families, and the ranking of their publication venues.