Tackling a Challenging Corpus for Early Detection of Gambling Disorder: UNSL at MentalRiskES 2025

TL;DR

This paper presents methods for early detection of gambling disorder risk from social media data, achieving top results in a challenging challenge dataset, and highlights the need for improved data interpretation.

Contribution

Introduces three CPI+DMC-based methods using advanced language models for classifying gambling risk, with top-tier performance in a competitive challenge.

Findings

Two methods achieved top positions in challenge results.

Difficulty in distinguishing high and low risk users was observed.

Highlights the importance of data quality and interpretability in ERD systems.

Abstract

Gambling disorder is a complex behavioral addiction that is challenging to understand and address, with severe physical, psychological, and social consequences. Early Risk Detection (ERD) on the Web has become a key task in the scientific community for identifying early signs of mental health behaviors based on social media activity. This work presents our participation in the MentalRiskES 2025 challenge, specifically in Task 1, aimed at classifying users at high or low risk of developing a gambling-related disorder. We proposed three methods based on a CPI+DMC approach, addressing predictive effectiveness and decision-making speed as independent objectives. The components were implemented using the SS3, BERT with extended vocabulary, and SBERT models, followed by decision policies based on historical user analysis. Although it was a challenging corpus, two of our proposals achieved the top two positions in the official results, performing notably in decision metrics. Further analysis revealed some difficulty in distinguishing between users at high and low risk, reinforcing the need to explore strategies to improve data interpretation and quality, and to promote more transparent and reliable ERD systems for mental disorders.