Fighting the COVID-19 Infodemic with a Holistic BERT Ensemble

Georgios Tziafas; Konstantinos Kogkalidis; Tommaso Caselli

doi:10.18653/v1/2021.nlp4if-1.18

Fighting the COVID-19 Infodemic with a Holistic BERT Ensemble

Georgios Tziafas, Konstantinos Kogkalidis, Tommaso Caselli

Computational Linguistics (CL)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

2 Citations (Scopus)

48 Downloads (Pure)

Abstract

This paper describes the TOKOFOU system, an ensemble model for misinformation detection tasks based on six different transformer-based pre-trained encoders, implemented in the context of the COVID-19 Infodemic Shared Task for English. We fine tune each model on each of the task's questions and aggregate their prediction scores using a majority voting approach. TOKOFOU obtains an overall F1 score of 89.7%, ranking first.

Original language	English
Title of host publication	Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda
Editors	Anna Feldman, Giovanni Da San Martino, Chris Leberknight, Preslav Nakov
Publisher	Association for Computational Linguistics (ACL)
Pages	119-124
Number of pages	6
DOIs	https://doi.org/10.18653/v1/2021.nlp4if-1.18
Publication status	Published - 13-Jun-2021

Keywords

misinformation
fake news
social media
COVID-19

Access to Document

10.18653/v1/2021.nlp4if-1.18Licence: CC BY

Fighting the COVID-19 Infodemic with a Holistic BERT EnsembleFinal publisher's version, 241 KBLicence: CC BY

Handle.net

Persistent link

Cite this

Tziafas, G., Kogkalidis, K., & Caselli, T. (2021). Fighting the COVID-19 Infodemic with a Holistic BERT Ensemble. In A. Feldman, G. Da San Martino, C. Leberknight, & P. Nakov (Eds.), Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda (pp. 119-124). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2021.nlp4if-1.18

Tziafas, Georgios ; Kogkalidis, Konstantinos ; Caselli, Tommaso. / Fighting the COVID-19 Infodemic with a Holistic BERT Ensemble. Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda. editor / Anna Feldman ; Giovanni Da San Martino ; Chris Leberknight ; Preslav Nakov. Association for Computational Linguistics (ACL), 2021. pp. 119-124

@inproceedings{aea25aa41b6a4919a38501eb74b45394,

title = "Fighting the COVID-19 Infodemic with a Holistic BERT Ensemble",

abstract = "This paper describes the TOKOFOU system, an ensemble model for misinformation detection tasks based on six different transformer-based pre-trained encoders, implemented in the context of the COVID-19 Infodemic Shared Task for English. We fine tune each model on each of the task's questions and aggregate their prediction scores using a majority voting approach. TOKOFOU obtains an overall F1 score of 89.7%, ranking first.",

keywords = "misinformation, fake news, social media, COVID-19",

author = "Georgios Tziafas and Konstantinos Kogkalidis and Tommaso Caselli",

year = "2021",

month = jun,

day = "13",

doi = "10.18653/v1/2021.nlp4if-1.18",

language = "English",

pages = "119--124",

editor = "Anna Feldman and {Da San Martino}, Giovanni and Chris Leberknight and Preslav Nakov",

booktitle = "Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda",

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

}

Tziafas, G, Kogkalidis, K & Caselli, T 2021, Fighting the COVID-19 Infodemic with a Holistic BERT Ensemble. in A Feldman, G Da San Martino, C Leberknight & P Nakov (eds), Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda. Association for Computational Linguistics (ACL), pp. 119-124. https://doi.org/10.18653/v1/2021.nlp4if-1.18

Fighting the COVID-19 Infodemic with a Holistic BERT Ensemble. / Tziafas, Georgios; Kogkalidis, Konstantinos; Caselli, Tommaso.
Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda. ed. / Anna Feldman; Giovanni Da San Martino; Chris Leberknight; Preslav Nakov. Association for Computational Linguistics (ACL), 2021. p. 119-124.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Fighting the COVID-19 Infodemic with a Holistic BERT Ensemble

AU - Tziafas, Georgios

AU - Kogkalidis, Konstantinos

AU - Caselli, Tommaso

PY - 2021/6/13

Y1 - 2021/6/13

N2 - This paper describes the TOKOFOU system, an ensemble model for misinformation detection tasks based on six different transformer-based pre-trained encoders, implemented in the context of the COVID-19 Infodemic Shared Task for English. We fine tune each model on each of the task's questions and aggregate their prediction scores using a majority voting approach. TOKOFOU obtains an overall F1 score of 89.7%, ranking first.

AB - This paper describes the TOKOFOU system, an ensemble model for misinformation detection tasks based on six different transformer-based pre-trained encoders, implemented in the context of the COVID-19 Infodemic Shared Task for English. We fine tune each model on each of the task's questions and aggregate their prediction scores using a majority voting approach. TOKOFOU obtains an overall F1 score of 89.7%, ranking first.

KW - misinformation

KW - fake news

KW - social media

KW - COVID-19

UR - https://www.mendeley.com/catalogue/7436edba-8580-30cb-be8c-75f35bb9b709/

U2 - 10.18653/v1/2021.nlp4if-1.18

DO - 10.18653/v1/2021.nlp4if-1.18

M3 - Conference contribution

SP - 119

EP - 124

BT - Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda

A2 - Feldman, Anna

A2 - Da San Martino, Giovanni

A2 - Leberknight, Chris

A2 - Nakov, Preslav

PB - Association for Computational Linguistics (ACL)

ER -

Tziafas G, Kogkalidis K, Caselli T. Fighting the COVID-19 Infodemic with a Holistic BERT Ensemble. In Feldman A, Da San Martino G, Leberknight C, Nakov P, editors, Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda. Association for Computational Linguistics (ACL). 2021. p. 119-124 doi: 10.18653/v1/2021.nlp4if-1.18

Fighting the COVID-19 Infodemic with a Holistic BERT Ensemble

Abstract

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

Cite this