This paper presents the MentalRiskES shared task organized at IberLEF 2024, as part of the 40th International Conference of the Spanish Society for Natural Language Processing. This task aims to promote the early detection of mental risk disorders in Spanish. We propose three detection tasks: Task 1 to detect risk for depression or anxiety, Task 2 to detect risk for depression or anxiety but determining contextual risk factors and Task 3 to identify whether a subject is at risk for suicidal ideation. Furthermore, we asked participants to submit measurements of carbon emissions for their systems, emphasizing the need for sustainable natural language processing practices. In this second edition, 28 teams registered, 12 submitted results, and 10 presented papers. Most teams experimented with Transformers, including features, data augmentation, and preprocessing techniques.
© 2008-2024 Fundación Dialnet · Todos los derechos reservados