@inproceedings{saha-etal-2023-vio,
title = "Vio-Lens: A Novel Dataset of Annotated Social Network Posts Leading to Different Forms of Communal Violence and its Evaluation",
author = "Saha, Sourav and
Junaed, Jahedul Alam and
Saleki, Maryam and
Sen Sharma, Arnab and
Rifat, Mohammad Rashidujjaman and
Rahouti, Mohamed and
Ahmed, Syed Ishtiaque and
Mohammed, Nabeel and
Amin, Mohammad Ruhul",
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-1.9",
doi = "10.18653/v1/2023.banglalp-1.9",
pages = "72--84",
abstract = "This paper presents a computational approach for creating a dataset on communal violence in the context of Bangladesh and West Bengal of India and benchmark evaluation. In recent years, social media has been used as a weapon by factions of different religions and backgrounds to incite hatred, resulting in physical communal violence and causing death and destruction. To prevent such abusive use of online platforms, we propose a framework for classifying online posts using an adaptive question-based approach. We collected more than 168,000 YouTube comments from a set of manually selected videos known for inciting violence in Bangladesh and West Bengal. Using both unsupervised and later semi-supervised topic modeling methods on those unstructured data, we discovered the major word clusters to interpret the related topics of peace and violence. Topic words were later used to select 20,142 posts related to peace and violence of which we annotated a total of 6,046 posts. Finally, we applied different modeling techniques based on linguistic features, and sentence transformers to benchmark the labeled dataset with the best-performing model reaching {\textasciitilde}71{\%} macro F1 score.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saha-etal-2023-vio">
<titleInfo>
<title>Vio-Lens: A Novel Dataset of Annotated Social Network Posts Leading to Different Forms of Communal Violence and its Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sourav</namePart>
<namePart type="family">Saha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jahedul</namePart>
<namePart type="given">Alam</namePart>
<namePart type="family">Junaed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maryam</namePart>
<namePart type="family">Saleki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arnab</namePart>
<namePart type="family">Sen Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Rashidujjaman</namePart>
<namePart type="family">Rifat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Rahouti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Syed</namePart>
<namePart type="given">Ishtiaque</namePart>
<namePart type="family">Ahmed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nabeel</namePart>
<namePart type="family">Mohammed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Ruhul</namePart>
<namePart type="family">Amin</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>This paper presents a computational approach for creating a dataset on communal violence in the context of Bangladesh and West Bengal of India and benchmark evaluation. In recent years, social media has been used as a weapon by factions of different religions and backgrounds to incite hatred, resulting in physical communal violence and causing death and destruction. To prevent such abusive use of online platforms, we propose a framework for classifying online posts using an adaptive question-based approach. We collected more than 168,000 YouTube comments from a set of manually selected videos known for inciting violence in Bangladesh and West Bengal. Using both unsupervised and later semi-supervised topic modeling methods on those unstructured data, we discovered the major word clusters to interpret the related topics of peace and violence. Topic words were later used to select 20,142 posts related to peace and violence of which we annotated a total of 6,046 posts. Finally, we applied different modeling techniques based on linguistic features, and sentence transformers to benchmark the labeled dataset with the best-performing model reaching ~71% macro F1 score.</abstract>
<identifier type="citekey">saha-etal-2023-vio</identifier>
<identifier type="doi">10.18653/v1/2023.banglalp-1.9</identifier>
<location>
<url>https://aclanthology.org/2023.banglalp-1.9</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>72</start>
<end>84</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Vio-Lens: A Novel Dataset of Annotated Social Network Posts Leading to Different Forms of Communal Violence and its Evaluation
%A Saha, Sourav
%A Junaed, Jahedul Alam
%A Saleki, Maryam
%A Sen Sharma, Arnab
%A Rifat, Mohammad Rashidujjaman
%A Rahouti, Mohamed
%A Ahmed, Syed Ishtiaque
%A Mohammed, Nabeel
%A Amin, Mohammad Ruhul
%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 saha-etal-2023-vio
%X This paper presents a computational approach for creating a dataset on communal violence in the context of Bangladesh and West Bengal of India and benchmark evaluation. In recent years, social media has been used as a weapon by factions of different religions and backgrounds to incite hatred, resulting in physical communal violence and causing death and destruction. To prevent such abusive use of online platforms, we propose a framework for classifying online posts using an adaptive question-based approach. We collected more than 168,000 YouTube comments from a set of manually selected videos known for inciting violence in Bangladesh and West Bengal. Using both unsupervised and later semi-supervised topic modeling methods on those unstructured data, we discovered the major word clusters to interpret the related topics of peace and violence. Topic words were later used to select 20,142 posts related to peace and violence of which we annotated a total of 6,046 posts. Finally, we applied different modeling techniques based on linguistic features, and sentence transformers to benchmark the labeled dataset with the best-performing model reaching ~71% macro F1 score.
%R 10.18653/v1/2023.banglalp-1.9
%U https://aclanthology.org/2023.banglalp-1.9
%U https://doi.org/10.18653/v1/2023.banglalp-1.9
%P 72-84
Markdown (Informal)
[Vio-Lens: A Novel Dataset of Annotated Social Network Posts Leading to Different Forms of Communal Violence and its Evaluation](https://aclanthology.org/2023.banglalp-1.9) (Saha et al., BanglaLP 2023)
ACL
- Sourav Saha, Jahedul Alam Junaed, Maryam Saleki, Arnab Sen Sharma, Mohammad Rashidujjaman Rifat, Mohamed Rahouti, Syed Ishtiaque Ahmed, Nabeel Mohammed, and Mohammad Ruhul Amin. 2023. Vio-Lens: A Novel Dataset of Annotated Social Network Posts Leading to Different Forms of Communal Violence and its Evaluation. In Proceedings of the First Workshop on Bangla Language Processing (BLP-2023), pages 72–84, Singapore. Association for Computational Linguistics.