Transformers to Fight the COVID-19 Infodemic

Lasitha Uyangodage; Tharindu Ranasinghe; Hansi Hettiarachchi

doi:10.18653/v1/2021.nlp4if-1.20

Transformers to Fight the COVID-19 Infodemic

Lasitha Uyangodage, Tharindu Ranasinghe, Hansi Hettiarachchi

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

The massive spread of false information on social media has become a global risk especially in a global pandemic situation like COVID-19. False information detection has thus become a surging research topic in recent months. NLP4IF-2021 shared task on fighting the COVID-19 infodemic has been organised to strengthen the research in false information detection where the participants are asked to predict seven different binary labels regarding false information in a tweet. The shared task has been organised in three languages; Arabic, Bulgarian and English. In this paper, we present our approach to tackle the task objective using transformers. Overall, our approach achieves a 0.707 mean F1 score in Arabic, 0.578 mean F1 score in Bulgarian and 0.864 mean F1 score in English ranking 4th place in all the languages.

Original language	English
Title of host publication	Proceedings of the 4th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE 2021)
Publisher	Association for Computational Linguistics (ACL)
Pages	130-135
Number of pages	6
DOIs	https://doi.org/10.18653/v1/2021.nlp4if-1.20
Publication status	Published - Jun 2021

Bibliographical note

Access to Document

10.18653/v1/2021.nlp4if-1.20Licence: CC BY 4.0

Uyangodageetal_2021_VoR
Copyright © 2021 Association for Computational Linguistics.licensed on a Creative Commons Attribution 4.0 International License.
Final published version, 492 KBLicence: CC BY 4.0

Cite this

@inproceedings{b7eccad746434b10bd69630cc8cb2b66,

title = "Transformers to Fight the COVID-19 Infodemic",

abstract = "The massive spread of false information on social media has become a global risk especially in a global pandemic situation like COVID-19. False information detection has thus become a surging research topic in recent months. NLP4IF-2021 shared task on fighting the COVID-19 infodemic has been organised to strengthen the research in false information detection where the participants are asked to predict seven different binary labels regarding false information in a tweet. The shared task has been organised in three languages; Arabic, Bulgarian and English. In this paper, we present our approach to tackle the task objective using transformers. Overall, our approach achieves a 0.707 mean F1 score in Arabic, 0.578 mean F1 score in Bulgarian and 0.864 mean F1 score in English ranking 4th place in all the languages.",

author = "Lasitha Uyangodage and Tharindu Ranasinghe and Hansi Hettiarachchi",

note = "Copyright {\textcopyright} 2021 Association for Computational Linguistics.licensed on a Creative Commons Attribution 4.0 International License.",

year = "2021",

month = jun,

doi = "10.18653/v1/2021.nlp4if-1.20",

language = "English",

pages = "130--135",

booktitle = "Proceedings of the 4th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE 2021)",

publisher = "Association for Computational Linguistics (ACL)",

address = "United States",

}

Transformers to Fight the COVID-19 Infodemic. / Uyangodage, Lasitha; Ranasinghe, Tharindu; Hettiarachchi, Hansi.
Proceedings of the 4th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE 2021). Association for Computational Linguistics (ACL), 2021. p. 130-135.

Research output: Chapter in Book/Published conference output › Conference publication

TY - GEN

T1 - Transformers to Fight the COVID-19 Infodemic

AU - Uyangodage, Lasitha

AU - Ranasinghe, Tharindu

AU - Hettiarachchi, Hansi

PY - 2021/6

Y1 - 2021/6

N2 - The massive spread of false information on social media has become a global risk especially in a global pandemic situation like COVID-19. False information detection has thus become a surging research topic in recent months. NLP4IF-2021 shared task on fighting the COVID-19 infodemic has been organised to strengthen the research in false information detection where the participants are asked to predict seven different binary labels regarding false information in a tweet. The shared task has been organised in three languages; Arabic, Bulgarian and English. In this paper, we present our approach to tackle the task objective using transformers. Overall, our approach achieves a 0.707 mean F1 score in Arabic, 0.578 mean F1 score in Bulgarian and 0.864 mean F1 score in English ranking 4th place in all the languages.

AB - The massive spread of false information on social media has become a global risk especially in a global pandemic situation like COVID-19. False information detection has thus become a surging research topic in recent months. NLP4IF-2021 shared task on fighting the COVID-19 infodemic has been organised to strengthen the research in false information detection where the participants are asked to predict seven different binary labels regarding false information in a tweet. The shared task has been organised in three languages; Arabic, Bulgarian and English. In this paper, we present our approach to tackle the task objective using transformers. Overall, our approach achieves a 0.707 mean F1 score in Arabic, 0.578 mean F1 score in Bulgarian and 0.864 mean F1 score in English ranking 4th place in all the languages.

UR - https://www.lens.org/078-428-912-739-287

UR - https://arxiv.org/abs/2104.12201

U2 - 10.18653/v1/2021.nlp4if-1.20

DO - 10.18653/v1/2021.nlp4if-1.20

M3 - Conference publication

SP - 130

EP - 135

BT - Proceedings of the 4th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE 2021)

PB - Association for Computational Linguistics (ACL)

ER -

Transformers to Fight the COVID-19 Infodemic

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this