@inproceedings{rahman-etal-2025-cuets,
title = "{CUET}{'}s{\_}{W}hite{\_}{W}alkers@{LT}-{EDI} 2025: Racial Hoax Detection in Code-Mixed on Social Media Data",
author = "Rahman, Md. Mizanur and
Abrar, Jidan Al and
Kawser, Md. Siddikul Imam and
Islam, Ariful and
Naib, Md. Mubasshir and
Murad, Hasan",
editor = "Gkirtzou, Katerina and
{\v{Z}}itnik, Slavko and
Gracia, Jorge and
Gromann, Dagmar and
di Buono, Maria Pia and
Monti, Johanna and
Ionov, Maxim",
booktitle = "Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion",
month = sep,
year = "2025",
address = "Naples, Italy",
publisher = "Unior Press",
url = "https://aclanthology.org/2025.ltedi-1.10/",
pages = "63--67",
ISBN = "978-88-6719-334-9",
abstract = "False narratives that manipulate racial tensions are increasingly prevalent on social media, often blending languages and cultural references to enhance reach and believability. Among them, racial hoaxes produce unique harm by fabricating events targeting specific communities, social division and fueling misinformation. This paper presents a novel approach to detecting racial hoaxes in code-mixed Hindi-English social media data. Using a carefully constructed training pipeline, we have fine-tuned the XLM-RoBERTa-base multilingual transformer for training the shared task data. Our approach has incorporated task-specific preprocessing, clear methodology, and extensive hyperparameter tuning. After developing our model, we tested and evaluated it on the LT-EDI@LDK 2025 shared task dataset. Our system achieved the highest performance among all the international participants with an F1-score of 0.75, ranking 1st on the official leaderboard."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rahman-etal-2025-cuets">
<titleInfo>
<title>CUET’s_White_Walkers@LT-EDI 2025: Racial Hoax Detection in Code-Mixed on Social Media Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Mizanur</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jidan</namePart>
<namePart type="given">Al</namePart>
<namePart type="family">Abrar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Siddikul</namePart>
<namePart type="given">Imam</namePart>
<namePart type="family">Kawser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ariful</namePart>
<namePart type="family">Islam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Mubasshir</namePart>
<namePart type="family">Naib</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>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katerina</namePart>
<namePart type="family">Gkirtzou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Slavko</namePart>
<namePart type="family">Žitnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Gracia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dagmar</namePart>
<namePart type="family">Gromann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Pia</namePart>
<namePart type="family">di Buono</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johanna</namePart>
<namePart type="family">Monti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maxim</namePart>
<namePart type="family">Ionov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Unior Press</publisher>
<place>
<placeTerm type="text">Naples, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-88-6719-334-9</identifier>
</relatedItem>
<abstract>False narratives that manipulate racial tensions are increasingly prevalent on social media, often blending languages and cultural references to enhance reach and believability. Among them, racial hoaxes produce unique harm by fabricating events targeting specific communities, social division and fueling misinformation. This paper presents a novel approach to detecting racial hoaxes in code-mixed Hindi-English social media data. Using a carefully constructed training pipeline, we have fine-tuned the XLM-RoBERTa-base multilingual transformer for training the shared task data. Our approach has incorporated task-specific preprocessing, clear methodology, and extensive hyperparameter tuning. After developing our model, we tested and evaluated it on the LT-EDI@LDK 2025 shared task dataset. Our system achieved the highest performance among all the international participants with an F1-score of 0.75, ranking 1st on the official leaderboard.</abstract>
<identifier type="citekey">rahman-etal-2025-cuets</identifier>
<location>
<url>https://aclanthology.org/2025.ltedi-1.10/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>63</start>
<end>67</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CUET’s_White_Walkers@LT-EDI 2025: Racial Hoax Detection in Code-Mixed on Social Media Data
%A Rahman, Md. Mizanur
%A Abrar, Jidan Al
%A Kawser, Md. Siddikul Imam
%A Islam, Ariful
%A Naib, Md. Mubasshir
%A Murad, Hasan
%Y Gkirtzou, Katerina
%Y Žitnik, Slavko
%Y Gracia, Jorge
%Y Gromann, Dagmar
%Y di Buono, Maria Pia
%Y Monti, Johanna
%Y Ionov, Maxim
%S Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion
%D 2025
%8 September
%I Unior Press
%C Naples, Italy
%@ 978-88-6719-334-9
%F rahman-etal-2025-cuets
%X False narratives that manipulate racial tensions are increasingly prevalent on social media, often blending languages and cultural references to enhance reach and believability. Among them, racial hoaxes produce unique harm by fabricating events targeting specific communities, social division and fueling misinformation. This paper presents a novel approach to detecting racial hoaxes in code-mixed Hindi-English social media data. Using a carefully constructed training pipeline, we have fine-tuned the XLM-RoBERTa-base multilingual transformer for training the shared task data. Our approach has incorporated task-specific preprocessing, clear methodology, and extensive hyperparameter tuning. After developing our model, we tested and evaluated it on the LT-EDI@LDK 2025 shared task dataset. Our system achieved the highest performance among all the international participants with an F1-score of 0.75, ranking 1st on the official leaderboard.
%U https://aclanthology.org/2025.ltedi-1.10/
%P 63-67
Markdown (Informal)
[CUET’s_White_Walkers@LT-EDI 2025: Racial Hoax Detection in Code-Mixed on Social Media Data](https://aclanthology.org/2025.ltedi-1.10/) (Rahman et al., LTEDI 2025)
ACL
- Md. Mizanur Rahman, Jidan Al Abrar, Md. Siddikul Imam Kawser, Ariful Islam, Md. Mubasshir Naib, and Hasan Murad. 2025. CUET’s_White_Walkers@LT-EDI 2025: Racial Hoax Detection in Code-Mixed on Social Media Data. In Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion, pages 63–67, Naples, Italy. Unior Press.