RT Conference Proceedings
T1 I2C-UHU at EXIST2024: Learning from Divergence and Perspectivism for Sexism Identification and Source Intent Classification
A1 Guerrero García, Manuel
A1 Cerrejón Naranjo, Manuel
A1 Mata Vázquez, Jacinto
A1 Pachón Álvarez, Victoria
AB In this paper, we present the contributions of the I2C-UHU team to the EXIST2024 Lab at CLEF 2024, focusingon the identification of sexism and the classification of source intent in social media texts. State-of-the-arttransformer models are employed to address the complex and nuanced nature of sexist language. We adopt atwo-fold approach: firstly, classifying tweets as sexist or non-sexist, and secondly, categorizing sexist tweets basedon intent. Our innovative approach, employing Learning with Disagreement, incorporates diverse perspectivesfrom multiple annotators, enhancing the robustness and accuracy of our models. We detail our data preprocessing,augmentation techniques, and hyperparameter optimization strategies. Our results in the competition demonstratedeffectiveness, with our entries achieving positive rankings in the two tasks in which we participated. InTask 1, we secured the 10th position out of 70 participants on the hard labels leaderboard and the 13th positionout of 40 for soft labels. In Task 2, we achieved the 11th position out of 46 participants for hard labels and the17th position out of 35 in the best run for soft labels. Our findings provide a foundation for future research andpractical applications in social media moderation and policy-making.
PB CEUR-WS
SN 1613-0073
YR 2024
FD 2024
LK https://hdl.handle.net/10272/24655
UL https://hdl.handle.net/10272/24655
LA eng
NO Guerrero-García, M., Cerrejón-Naranjo, M., Mata-Vázquez, J., & Pachón-Álvarez, V. (2024). I2C-UHU at EXIST2024: Learning from Divergence and Perspectivism for Sexism Identification and Source Intent Classification. CEUR Workshop Proceedings, 3740, 1026-1042.
NO This paper is part of the I+D+i Project titled “Conspiracy Theories and hate speech online: Comparisonof patterns in narratives and social networks about COVID-19, immigrants, refugees and LGBTI people[NON-CONSPIRA-HATE!]”, PID2021-123983OB-I00, funded by MCIN/AEI/10.13039/501100011033/ and by“ERDF/EU”.
DS Repositorio Institucional de la Universidad de Huelva
RD 31 may 2026