Early Detection of Depression and Eating Disorders in Spanish: UNSL at MentalRiskES 2023

TL;DR

This paper presents Transformer-based models with decision policies for early detection of depression and eating disorders in Spanish Telegram users, achieving high accuracy and low latency in a novel challenge.

Contribution

It introduces a new early detection framework using Transformers with history-based decision policies for Spanish mental health risk detection.

Findings

Second-best performance in classification and latency

Effective use of extended vocabulary for key terms

Demonstrated robustness of early detection approach

Abstract

MentalRiskES is a novel challenge that proposes to solve problems related to early risk detection for the Spanish language. The objective is to detect, as soon as possible, Telegram users who show signs of mental disorders considering different tasks. Task 1 involved the users' detection of eating disorders, Task 2 focused on depression detection, and Task 3 aimed at detecting an unknown disorder. These tasks were divided into subtasks, each one defining a resolution approach. Our research group participated in subtask A for Tasks 1 and 2: a binary classification problem that evaluated whether the users were positive or negative. To solve these tasks, we proposed models based on Transformers followed by a decision policy according to criteria defined by an early detection framework. One of the models presented an extended vocabulary with important words for each task to be solved. In addition, we applied a decision policy based on the history of predictions that the model performs during user evaluation. For Tasks 1 and 2, we obtained the second-best performance according to rankings based on classification and latency, demonstrating the effectiveness and consistency of our approaches for solving early detection problems in the Spanish language.