IR3218-UI at SemEval-2020 Task 12: Emoji Effects on Offensive Language IdentifiCation

Sandy Kurniawan, Indra Budi, Muhammad Okky Ibrohim


Abstract
In this paper, we present our approach and the results of our participation in OffensEval 2020. There are three sub-tasks in OffensEval 2020 namely offensive language identification (sub-task A), automatic categorization of offense types (sub-task B), and offense target identification (sub-task C). We participated in sub-task A of English OffensEval 2020. Our approach emphasizes on how the emoji affects offensive language identification. Our model used LSTM combined with GloVe pre-trained word vectors to identify offensive language on social media. The best model obtained macro F1-score of 0.88428.
Anthology ID:
2020.semeval-1.263
Volume:
Proceedings of the Fourteenth Workshop on Semantic Evaluation
Month:
December
Year:
2020
Address:
Barcelona (online)
Venues:
COLING | SemEval
SIGs:
SIGLEX | SIGSEM
Publisher:
International Committee for Computational Linguistics
Note:
Pages:
1998–2005
Language:
URL:
https://aclanthology.org/2020.semeval-1.263
DOI:
10.18653/v1/2020.semeval-1.263
Bibkey:
Cite (ACL):
Sandy Kurniawan, Indra Budi, and Muhammad Okky Ibrohim. 2020. IR3218-UI at SemEval-2020 Task 12: Emoji Effects on Offensive Language IdentifiCation. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 1998–2005, Barcelona (online). International Committee for Computational Linguistics.
Cite (Informal):
IR3218-UI at SemEval-2020 Task 12: Emoji Effects on Offensive Language IdentifiCation (Kurniawan et al., SemEval 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2020.semeval-1.263.pdf