@inproceedings{das-etal-2023-emptymind,
title = "{E}mpty{M}ind at {BLP}-2023 Task 1: A Transformer-based Hierarchical-{BERT} Model for {B}angla Violence-Inciting Text Detection",
author = "Das, Udoy and
Fatema, Karnis and
Mia, Md Ayon and
Yahan, Mahshar and
Mowla, Md Sajidul and
Ullah, Md Fayez and
Sarker, Arpita and
Murad, Hasan",
editor = "Alam, Firoj and
Kar, Sudipta and
Chowdhury, Shammur Absar and
Sadeque, Farig and
Amin, Ruhul",
booktitle = "Proceedings of the First Workshop on Bangla Language Processing (BLP-2023)",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.banglalp-1.19/",
doi = "10.18653/v1/2023.banglalp-1.19",
pages = "174--178",
abstract = "The availability of the internet has made it easier for people to share information via social media. People with ill intent can use this widespread availability of the internet to share violent content easily. A significant portion of social media users prefer using their regional language which makes it quite difficult to detect violence-inciting text. The objective of our research work is to detect Bangla violence-inciting text from social media content. A shared task on Bangla violence-inciting text detection has been organized by the First Bangla Language Processing Workshop (BLP) co-located with EMNLP, where the organizer has provided a dataset named VITD with three categories: nonviolence, passive violence, and direct violence text. To accomplish this task, we have implemented three machine learning models (RF, SVM, XGBoost), two deep learning models (LSTM, BiLSTM), and two transformer-based models (BanglaBERT, Hierarchical-BERT). We have conducted a comparative study among different models by training and evaluating each model on the VITD dataset. We have found that Hierarchical-BERT has provided the best result with an F1 score of 0.73797 on the test set and ranked 9th position among all participants in the shared task 1 of the BLP Workshop co-located with EMNLP 2023."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="das-etal-2023-emptymind">
<titleInfo>
<title>EmptyMind at BLP-2023 Task 1: A Transformer-based Hierarchical-BERT Model for Bangla Violence-Inciting Text Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Udoy</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karnis</namePart>
<namePart type="family">Fatema</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Ayon</namePart>
<namePart type="family">Mia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahshar</namePart>
<namePart type="family">Yahan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Sajidul</namePart>
<namePart type="family">Mowla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Fayez</namePart>
<namePart type="family">Ullah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arpita</namePart>
<namePart type="family">Sarker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hasan</namePart>
<namePart type="family">Murad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Bangla Language Processing (BLP-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudipta</namePart>
<namePart type="family">Kar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shammur</namePart>
<namePart type="given">Absar</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Farig</namePart>
<namePart type="family">Sadeque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruhul</namePart>
<namePart type="family">Amin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The availability of the internet has made it easier for people to share information via social media. People with ill intent can use this widespread availability of the internet to share violent content easily. A significant portion of social media users prefer using their regional language which makes it quite difficult to detect violence-inciting text. The objective of our research work is to detect Bangla violence-inciting text from social media content. A shared task on Bangla violence-inciting text detection has been organized by the First Bangla Language Processing Workshop (BLP) co-located with EMNLP, where the organizer has provided a dataset named VITD with three categories: nonviolence, passive violence, and direct violence text. To accomplish this task, we have implemented three machine learning models (RF, SVM, XGBoost), two deep learning models (LSTM, BiLSTM), and two transformer-based models (BanglaBERT, Hierarchical-BERT). We have conducted a comparative study among different models by training and evaluating each model on the VITD dataset. We have found that Hierarchical-BERT has provided the best result with an F1 score of 0.73797 on the test set and ranked 9th position among all participants in the shared task 1 of the BLP Workshop co-located with EMNLP 2023.</abstract>
<identifier type="citekey">das-etal-2023-emptymind</identifier>
<identifier type="doi">10.18653/v1/2023.banglalp-1.19</identifier>
<location>
<url>https://aclanthology.org/2023.banglalp-1.19/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>174</start>
<end>178</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EmptyMind at BLP-2023 Task 1: A Transformer-based Hierarchical-BERT Model for Bangla Violence-Inciting Text Detection
%A Das, Udoy
%A Fatema, Karnis
%A Mia, Md Ayon
%A Yahan, Mahshar
%A Mowla, Md Sajidul
%A Ullah, Md Fayez
%A Sarker, Arpita
%A Murad, Hasan
%Y Alam, Firoj
%Y Kar, Sudipta
%Y Chowdhury, Shammur Absar
%Y Sadeque, Farig
%Y Amin, Ruhul
%S Proceedings of the First Workshop on Bangla Language Processing (BLP-2023)
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F das-etal-2023-emptymind
%X The availability of the internet has made it easier for people to share information via social media. People with ill intent can use this widespread availability of the internet to share violent content easily. A significant portion of social media users prefer using their regional language which makes it quite difficult to detect violence-inciting text. The objective of our research work is to detect Bangla violence-inciting text from social media content. A shared task on Bangla violence-inciting text detection has been organized by the First Bangla Language Processing Workshop (BLP) co-located with EMNLP, where the organizer has provided a dataset named VITD with three categories: nonviolence, passive violence, and direct violence text. To accomplish this task, we have implemented three machine learning models (RF, SVM, XGBoost), two deep learning models (LSTM, BiLSTM), and two transformer-based models (BanglaBERT, Hierarchical-BERT). We have conducted a comparative study among different models by training and evaluating each model on the VITD dataset. We have found that Hierarchical-BERT has provided the best result with an F1 score of 0.73797 on the test set and ranked 9th position among all participants in the shared task 1 of the BLP Workshop co-located with EMNLP 2023.
%R 10.18653/v1/2023.banglalp-1.19
%U https://aclanthology.org/2023.banglalp-1.19/
%U https://doi.org/10.18653/v1/2023.banglalp-1.19
%P 174-178
Markdown (Informal)
[EmptyMind at BLP-2023 Task 1: A Transformer-based Hierarchical-BERT Model for Bangla Violence-Inciting Text Detection](https://aclanthology.org/2023.banglalp-1.19/) (Das et al., BanglaLP 2023)
ACL