@inproceedings{jafari-etal-2024-dragon,
title = "{DRAGON} at {FIGNEWS} 2024 Shared Task: a Dedicated {RAG} for {O}ctober 7th conflict News",
author = "Jafari, Sadegh and
Mahmoodzadeh, Mohsen and
Nazari, Vanooshe and
Bahmanyar, Razieh and
Burrows, Kathryn",
editor = "Habash, Nizar and
Bouamor, Houda and
Eskander, Ramy and
Tomeh, Nadi and
Abu Farha, Ibrahim and
Abdelali, Ahmed and
Touileb, Samia and
Hamed, Injy and
Onaizan, Yaser and
Alhafni, Bashar and
Antoun, Wissam and
Khalifa, Salam and
Haddad, Hatem and
Zitouni, Imed and
AlKhamissi, Badr and
Almatham, Rawan and
Mrini, Khalil",
booktitle = "Proceedings of the Second Arabic Natural Language Processing Conference",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.arabicnlp-1.58/",
doi = "10.18653/v1/2024.arabicnlp-1.58",
pages = "555--560",
abstract = "In this study, we present a novel approach to annotating bias and propaganda in social media data by leveraging topic modeling techniques. Utilizing the BERTopic tool, we performed topic modeling on the FIGNEWS Shared-task dataset, which initially comprised 13,500 samples. From this dataset, we identified 35 distinct topics and selected approximately 50 representative samples from each topic, resulting in a subset of 1,812 samples. These selected samples were meticulously annotated for bias and propaganda labels. Subsequently, we employed multiple methods like KNN, SVC, XGBoost, and RAG to develop a classifier capable of detecting bias and propaganda within social media content. Our approach demonstrates the efficacy of using topic modeling for efficient data subset selection and provides a robust foundation for improving the accuracy of bias and propaganda detection in large-scale social media datasets."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jafari-etal-2024-dragon">
<titleInfo>
<title>DRAGON at FIGNEWS 2024 Shared Task: a Dedicated RAG for October 7th conflict News</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sadegh</namePart>
<namePart type="family">Jafari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohsen</namePart>
<namePart type="family">Mahmoodzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vanooshe</namePart>
<namePart type="family">Nazari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Razieh</namePart>
<namePart type="family">Bahmanyar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kathryn</namePart>
<namePart type="family">Burrows</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Arabic Natural Language Processing Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramy</namePart>
<namePart type="family">Eskander</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Abu Farha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samia</namePart>
<namePart type="family">Touileb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bashar</namePart>
<namePart type="family">Alhafni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wissam</namePart>
<namePart type="family">Antoun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hatem</namePart>
<namePart type="family">Haddad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Badr</namePart>
<namePart type="family">AlKhamissi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rawan</namePart>
<namePart type="family">Almatham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Mrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this study, we present a novel approach to annotating bias and propaganda in social media data by leveraging topic modeling techniques. Utilizing the BERTopic tool, we performed topic modeling on the FIGNEWS Shared-task dataset, which initially comprised 13,500 samples. From this dataset, we identified 35 distinct topics and selected approximately 50 representative samples from each topic, resulting in a subset of 1,812 samples. These selected samples were meticulously annotated for bias and propaganda labels. Subsequently, we employed multiple methods like KNN, SVC, XGBoost, and RAG to develop a classifier capable of detecting bias and propaganda within social media content. Our approach demonstrates the efficacy of using topic modeling for efficient data subset selection and provides a robust foundation for improving the accuracy of bias and propaganda detection in large-scale social media datasets.</abstract>
<identifier type="citekey">jafari-etal-2024-dragon</identifier>
<identifier type="doi">10.18653/v1/2024.arabicnlp-1.58</identifier>
<location>
<url>https://aclanthology.org/2024.arabicnlp-1.58/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>555</start>
<end>560</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DRAGON at FIGNEWS 2024 Shared Task: a Dedicated RAG for October 7th conflict News
%A Jafari, Sadegh
%A Mahmoodzadeh, Mohsen
%A Nazari, Vanooshe
%A Bahmanyar, Razieh
%A Burrows, Kathryn
%Y Habash, Nizar
%Y Bouamor, Houda
%Y Eskander, Ramy
%Y Tomeh, Nadi
%Y Abu Farha, Ibrahim
%Y Abdelali, Ahmed
%Y Touileb, Samia
%Y Hamed, Injy
%Y Onaizan, Yaser
%Y Alhafni, Bashar
%Y Antoun, Wissam
%Y Khalifa, Salam
%Y Haddad, Hatem
%Y Zitouni, Imed
%Y AlKhamissi, Badr
%Y Almatham, Rawan
%Y Mrini, Khalil
%S Proceedings of the Second Arabic Natural Language Processing Conference
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F jafari-etal-2024-dragon
%X In this study, we present a novel approach to annotating bias and propaganda in social media data by leveraging topic modeling techniques. Utilizing the BERTopic tool, we performed topic modeling on the FIGNEWS Shared-task dataset, which initially comprised 13,500 samples. From this dataset, we identified 35 distinct topics and selected approximately 50 representative samples from each topic, resulting in a subset of 1,812 samples. These selected samples were meticulously annotated for bias and propaganda labels. Subsequently, we employed multiple methods like KNN, SVC, XGBoost, and RAG to develop a classifier capable of detecting bias and propaganda within social media content. Our approach demonstrates the efficacy of using topic modeling for efficient data subset selection and provides a robust foundation for improving the accuracy of bias and propaganda detection in large-scale social media datasets.
%R 10.18653/v1/2024.arabicnlp-1.58
%U https://aclanthology.org/2024.arabicnlp-1.58/
%U https://doi.org/10.18653/v1/2024.arabicnlp-1.58
%P 555-560
Markdown (Informal)
[DRAGON at FIGNEWS 2024 Shared Task: a Dedicated RAG for October 7th conflict News](https://aclanthology.org/2024.arabicnlp-1.58/) (Jafari et al., ArabicNLP 2024)
ACL