Sarcastic RoBERTa: A RoBERTa-Based Deep Neural Network Detecting Sarcasm on Twitter

Maciej Hercog; Piotr Jaroński; Jan Kolanowski; Paweł Mieczyński; Dawid Wiśniewski; Jędrzej Potoniec

doi:10.1007/978-3-031-12670-3_4

Scientific Information System of the Poznań University of Technology

PL EN

Main page / Publications / Sarcastic RoBERTa: A RoBERTa-Based Deep Neural Network Detecting Sarcasm on Twitter

Submit a comment

Chapter

Download BibTeX

Title

Sarcastic RoBERTa: A RoBERTa-Based Deep Neural Network Detecting Sarcasm on Twitter

Authors

Maciej Hercog (WIiT) ^{[ 1 ][ S ]}
Piotr Jaroński (WIiT) ^{[ 1 ][ S ]}
Jan Kolanowski (WIiT) ^{[ 1 ][ S ]}
Paweł Mieczyński (WIiT) ^{[ 1 ][ S ]}
Dawid Wiśniewski (WIiT) ^{[ 2 ][ 2.3 ][ P ]}
Jędrzej Potoniec (WIiT) ^{[ 2 ][ 2.3 ][ P ]}

^{[ 1 ]} Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | ^{[ 2 ]} Instytut Informatyki, Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | ^{[ S ]} student | ^{[ P ]} employee

Scientific discipline (Law 2.0)

[2.3] Information and communication technology

Year of publication

2022

Chapter type

chapter in monograph / paper

Publication language

english

Keywords

EN

Text classification
Sarcasm detection
RoBERTa
iSarcasm
SARC
Knowledge transfer

Abstract

EN Sarcastic RoBERTa is an approach to recognizing sarcastic tweets written in English. It is based on a pre-trained RoBERTa model supported by a 3-layer feed-forward fully-connected neural network. It establishes a new state-of-the-art result on the iSarcasm dataset, attaining the F1 score of 0.526, and being not far from the human performance of 0.616.

Date of online publication

26.07.2022

Pages (from - to)

46 - 52

DOI

10.1007/978-3-031-12670-3_4

URL

https://link.springer.com/chapter/10.1007/978-3-031-12670-3_4

Book

Big Data Analytics and Knowledge Discovery : 24th International Conference, DaWaK 2022, Vienna, Austria, August 22–24, 2022, Proceedings

Presented on

24th International Conference on Big Data Analytics and Knowledge Discovery DaWaK 2022, 22-24.08.2022, Vienna, Austria