RT Conference Proceedings
T1 I2C-UHU at MentalRiskES 2023: Detecting and Identifying Mental Disorder Risks in Social Media using Transformer-Based Models
A1 Vázquez Ramos, Laura
A1 Moreno García, Carlos
A1 Mata Vázquez, Jacinto
A1 Pachón Álvarez, Victoria
AB This paper presents the approaches proposed by the I2C Group to address MentalRiskES: EarlyDetection of Mental Disorder Risks in Spanish, as part of IberLEF 2023. Our proposal involvesdeveloping distinct transformer-based classifiers to tackle three specific tasks: i) Task1a:Binary classification for the detection of eating disorders, ii) Task1b: Simple regression for thedetection of eating disorders, and iii) Task2c: Multiclass classification for the detection ofdepression. The main approach consisted of fine-tuning pre-trained transformer-based models.For the binary tasks, diverse methodologies were employed to predict users based on thepredictions obtained from their individual messages. For the multiclass task, data augmentationapproaches were used to balance the minority classes messages. The final submittedpredictions achieved a Macro-F1 score of 0.641 for Task1a, ranking 19th out of 22 participants;an RMSE of 0.24 for Task1b, ranking 4th out of 17 participants; and a Macro-F1 score of 0.232for Task2c, ranking 4th out of 10 participants.
PB CEUR-WS
YR 2023
FD 2023
LK https://hdl.handle.net/10272/24614
UL https://hdl.handle.net/10272/24614
LA eng
NO Vázquez-Ramos, L; Moreno-García, C.; Mata-Vázquez, J., & Pachón-Álvarez, V. (2024). I2C-UHU at MentalRiskES 2023: Detecting and Identifying Mental Disorder Risks in Social Media using Transformer-Based Models. In Proceedings of the Iberian Languages Evaluation Forum (IberLEF 2023) colocated with the Conference of the Spanish Society for Natural Language Processing (SEPLN 2023), Jaén, Spain, September 26, 2023. CEUR Workshop Proceedings 3496
DS Repositorio Institucional de la Universidad de Huelva
RD 30 may 2026