UA at SemEval-2019 Task 5: Setting A Strong Linear Baseline for Hate Speech Detection

Carlos Perelló, David Tomás, Alberto Garcia-Garcia, Jose Garcia-Rodriguez, Jose Camacho-Collados


Abstract
This paper describes the system developed at the University of Alicante (UA) for the SemEval 2019 Task 5: Shared Task on Multilingual Detection of Hate. The purpose of this work is to build a strong baseline for hate speech detection, using a traditional machine learning approach with standard textual features, which could serve in a near future as a reference to compare with deep learning systems. We participated in both task A (Hate Speech Detection against Immigrants and Women) and task B (Aggressive behavior and Target Classification). Despite its simplicity, our system obtained a remarkable F1-score of 72.5 (sixth highest) and an accuracy of 73.6 (second highest) in Spanish (task A), outperforming more complex neural models from a total of 40 participant systems.
Anthology ID:
S19-2091
Volume:
Proceedings of the 13th International Workshop on Semantic Evaluation
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota, USA
Editors:
Jonathan May, Ekaterina Shutova, Aurelie Herbelot, Xiaodan Zhu, Marianna Apidianaki, Saif M. Mohammad
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
508–513
Language:
URL:
https://aclanthology.org/S19-2091
DOI:
10.18653/v1/S19-2091
Bibkey:
Cite (ACL):
Carlos Perelló, David Tomás, Alberto Garcia-Garcia, Jose Garcia-Rodriguez, and Jose Camacho-Collados. 2019. UA at SemEval-2019 Task 5: Setting A Strong Linear Baseline for Hate Speech Detection. In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 508–513, Minneapolis, Minnesota, USA. Association for Computational Linguistics.
Cite (Informal):
UA at SemEval-2019 Task 5: Setting A Strong Linear Baseline for Hate Speech Detection (Perelló et al., SemEval 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/S19-2091.pdf