The dataset contains Instagram messages from users who suffer from mental health disorders. There is a sample of messages per user. The annotations are made at the message level and indicate whether the user has a mental health disorder, as well as the context in which it occurs.
Language(s)
Spanish
Dataset description link
Year
2024
Domain
Health
Annotations
Each instance is assigned a binary label indicating whether the text contains hopeful language or not, and a multi-class label based on the type of hopeful language it contains.
Format
json
Data access
Register form
Publication
Mármol-Romero et al. (2024). Overview of MentalRiskES at IberLEF 2024: Early Detection of Mental Disorders Risk in Spanish. Procesamiento del Lenguaje Natural, 73: 435-448.
NLP Topic
Number of units
79975
Type of units
Telegram messages
Training set size
46411
Test set size
32343
Development set size
1221
