RT Conference Proceedings
T1 Identification of profession & occupation in Health-related Social Media using tweets in Spanish
A1 Pachón Álvarez, Victoria
A1 Mata Vázquez, Jacinto
A1 Domínguez Olmedo, Juan Luis
K1 Natural Language Processing
K1 Health-related Social Media
K1 Spanish BERT
K1 Transformer Models
K1 Text Classification
AB In this paper we present our approach and system description on Task 7a in ProfNer-ST: Identification of profession & occupation in Health related Social Media. Our main contribution is to show the effectiveness of using BETO-Spanish BERT for classification tasks in Spanish. In our experiments we compared several architectures based on transformers with others based on classical machine learning algorithms. With this approach, we achieved an F1-score of 0.92 for the positive class in the evaluation process
PB Association for Computational Linguistics (ACL)
SN 978-1-954085-31-2
YR 2021
FD 2021
LK https://hdl.handle.net/10272/27977
UL https://hdl.handle.net/10272/27977
LA eng
NO Victoria Pachón, Jacinto Mata Vázquez, and Juan Luís Domínguez Olmedo. 2021. Identification of profession & occupation in Health-related Social Media using tweets in Spanish. In Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task, pages 105–107, Mexico City, Mexico. Association for Computational Linguistics.
NO Conference Paper presentado en el 6th Workshop and Shared Tasks on Social Media Mining for Health (SMM4H 2021), evento internacional especializado en minería de redes sociales para salud, organizado en el marco de NAACL-HLT 2021. Indexado en Scopus (EID: 2-s2.0-85118327086).
DS Repositorio Institucional de la Universidad de Huelva
RD 25 jun 2026