Identification of profession & occupation in Health-related Social Media using tweets in Spanish
Loading...
Publication date
Advisors
Department
Research group
Center
Metrics
Export
Abstract
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
Unesco Subjects
Bibliographic citation
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.
Collections
The license for this item is described as Attribution 4.0 International