GAN-BERT: Adversarial Learning for Detection of Aggressive and Violent Incidents from Social Media

Hoang Thang Ta; Abu Bakar Siddiqur Rahman; Lotfollah Najjar; Alexander Gelbukh

GAN-BERT: Adversarial Learning for Detection of Aggressive and Violent Incidents from Social Media

Hoang Thang Ta, Abu Bakar Siddiqur Rahman, Lotfollah Najjar, Alexander Gelbukh

Centro de Investigación en Computación (CIC)

Research output: Contribution to journal › Conference article › peer-review

6 Scopus citations

Abstract

In this paper, we address Subtask 1 of Detection of Aggressive and Violent INCIdents from Social Media in Spanish (DA-VINCIS). We introduced our method, using text embeddings from pre-trained transformer models for the training process by GAN-BERT, an adversarial learning architecture. Finally, we obtained F1 of 74.43%, Precision of 74.08%, and Recall of 74.79% on Subtask 1.

Original language	English
Journal	CEUR Workshop Proceedings
Volume	3202
State	Published - 2022
Event	2022 Iberian Languages Evaluation Forum, IberLEF 2022 - A Coruna, Spain Duration: 20 Sep 2022 → …

Keywords

DA-VINCIS
GAN-BERT
IberLEF
NLP
Offensive Language
Text Classification
Violence Detection

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Cite this

@article{2c2ac74ef71e4fce967c0556eebb4aae,

title = "GAN-BERT: Adversarial Learning for Detection of Aggressive and Violent Incidents from Social Media",

abstract = "In this paper, we address Subtask 1 of Detection of Aggressive and Violent INCIdents from Social Media in Spanish (DA-VINCIS). We introduced our method, using text embeddings from pre-trained transformer models for the training process by GAN-BERT, an adversarial learning architecture. Finally, we obtained F1 of 74.43%, Precision of 74.08%, and Recall of 74.79% on Subtask 1.",

keywords = "DA-VINCIS, GAN-BERT, IberLEF, NLP, Offensive Language, Text Classification, Violence Detection",

author = "Ta, {Hoang Thang} and Rahman, {Abu Bakar Siddiqur} and Lotfollah Najjar and Alexander Gelbukh",

note = "Publisher Copyright: {\textcopyright} 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).; 2022 Iberian Languages Evaluation Forum, IberLEF 2022 ; Conference date: 20-09-2022",

year = "2022",

language = "Ingl{\'e}s",

volume = "3202",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

publisher = "CEUR-WS",

}

TY - JOUR

T1 - GAN-BERT

T2 - 2022 Iberian Languages Evaluation Forum, IberLEF 2022

AU - Ta, Hoang Thang

AU - Rahman, Abu Bakar Siddiqur

AU - Najjar, Lotfollah

AU - Gelbukh, Alexander

PY - 2022

Y1 - 2022

N2 - In this paper, we address Subtask 1 of Detection of Aggressive and Violent INCIdents from Social Media in Spanish (DA-VINCIS). We introduced our method, using text embeddings from pre-trained transformer models for the training process by GAN-BERT, an adversarial learning architecture. Finally, we obtained F1 of 74.43%, Precision of 74.08%, and Recall of 74.79% on Subtask 1.

AB - In this paper, we address Subtask 1 of Detection of Aggressive and Violent INCIdents from Social Media in Spanish (DA-VINCIS). We introduced our method, using text embeddings from pre-trained transformer models for the training process by GAN-BERT, an adversarial learning architecture. Finally, we obtained F1 of 74.43%, Precision of 74.08%, and Recall of 74.79% on Subtask 1.

KW - DA-VINCIS

KW - GAN-BERT

KW - IberLEF

KW - NLP

KW - Offensive Language

KW - Text Classification

KW - Violence Detection

UR - http://www.scopus.com/inward/record.url?scp=85137331642&partnerID=8YFLogxK

M3 - Artículo de la conferencia

AN - SCOPUS:85137331642

SN - 1613-0073

VL - 3202

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

Y2 - 20 September 2022

ER -

GAN-BERT: Adversarial Learning for Detection of Aggressive and Violent Incidents from Social Media

Abstract

Keywords

UN SDGs

Other files and links

Cite this