@inproceedings{aodhora-etal-2025-cuet,
title = "{CUET}{\_}{H}ate{S}hield@{NLU} of {D}evanagari Script Languages 2025: Transformer-Based Hate Speech Detection in {D}evanagari Script Languages",
author = "Aodhora, Sumaiya Rahman and
Ahsan, Shawly and
Hoque, Mohammed Moshiul",
editor = "Sarveswaran, Kengatharaiyer and
Vaidya, Ashwini and
Krishna Bal, Bal and
Shams, Sana and
Thapa, Surendrabikram",
booktitle = "Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025)",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2025.chipsal-1.28/",
pages = "260--266",
abstract = "Social media has become a vital platform for information exchange and free expression, yet its open nature also contributes to the spread of harmful content, including hate speech, cyberbullying, and offensive language, posing serious risks to societal well-being. Such content is linked to adverse impacts, including mental health issues. This study aims to develop an automated system for detecting hate speech in Devanagari script languages, enabling efficient moderation and prompt intervention. Our approach utilizes a fine-tuned transformer model to classify offensive content. We experimented with various machine learning (Logistic Regression, SVM, Ensemble methods) and deep learning architectures (CNN, BiLSTM, CNN-BiLSTM) alongside transformer-based models (Indic-SBERT, m-BERT, MuRIL, Indic-SBERT, XLM-R). Notably, the fine-tuned XLM-Roberta model achieved the highest performance, reaching a macro-average F1-score of 0.74, demonstrating its efficacy in detecting hate speech in Devanagari script languages. However, the model we submitted achieved a macro-average F1-score of 0.73, securing 13th place in the subtask."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aodhora-etal-2025-cuet">
<titleInfo>
<title>CUET_HateShield@NLU of Devanagari Script Languages 2025: Transformer-Based Hate Speech Detection in Devanagari Script Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sumaiya</namePart>
<namePart type="given">Rahman</namePart>
<namePart type="family">Aodhora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shawly</namePart>
<namePart type="family">Ahsan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="given">Moshiul</namePart>
<namePart type="family">Hoque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kengatharaiyer</namePart>
<namePart type="family">Sarveswaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashwini</namePart>
<namePart type="family">Vaidya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bal</namePart>
<namePart type="family">Krishna Bal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sana</namePart>
<namePart type="family">Shams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surendrabikram</namePart>
<namePart type="family">Thapa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Social media has become a vital platform for information exchange and free expression, yet its open nature also contributes to the spread of harmful content, including hate speech, cyberbullying, and offensive language, posing serious risks to societal well-being. Such content is linked to adverse impacts, including mental health issues. This study aims to develop an automated system for detecting hate speech in Devanagari script languages, enabling efficient moderation and prompt intervention. Our approach utilizes a fine-tuned transformer model to classify offensive content. We experimented with various machine learning (Logistic Regression, SVM, Ensemble methods) and deep learning architectures (CNN, BiLSTM, CNN-BiLSTM) alongside transformer-based models (Indic-SBERT, m-BERT, MuRIL, Indic-SBERT, XLM-R). Notably, the fine-tuned XLM-Roberta model achieved the highest performance, reaching a macro-average F1-score of 0.74, demonstrating its efficacy in detecting hate speech in Devanagari script languages. However, the model we submitted achieved a macro-average F1-score of 0.73, securing 13th place in the subtask.</abstract>
<identifier type="citekey">aodhora-etal-2025-cuet</identifier>
<location>
<url>https://aclanthology.org/2025.chipsal-1.28/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>260</start>
<end>266</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CUET_HateShield@NLU of Devanagari Script Languages 2025: Transformer-Based Hate Speech Detection in Devanagari Script Languages
%A Aodhora, Sumaiya Rahman
%A Ahsan, Shawly
%A Hoque, Mohammed Moshiul
%Y Sarveswaran, Kengatharaiyer
%Y Vaidya, Ashwini
%Y Krishna Bal, Bal
%Y Shams, Sana
%Y Thapa, Surendrabikram
%S Proceedings of the First Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2025)
%D 2025
%8 January
%I International Committee on Computational Linguistics
%C Abu Dhabi, UAE
%F aodhora-etal-2025-cuet
%X Social media has become a vital platform for information exchange and free expression, yet its open nature also contributes to the spread of harmful content, including hate speech, cyberbullying, and offensive language, posing serious risks to societal well-being. Such content is linked to adverse impacts, including mental health issues. This study aims to develop an automated system for detecting hate speech in Devanagari script languages, enabling efficient moderation and prompt intervention. Our approach utilizes a fine-tuned transformer model to classify offensive content. We experimented with various machine learning (Logistic Regression, SVM, Ensemble methods) and deep learning architectures (CNN, BiLSTM, CNN-BiLSTM) alongside transformer-based models (Indic-SBERT, m-BERT, MuRIL, Indic-SBERT, XLM-R). Notably, the fine-tuned XLM-Roberta model achieved the highest performance, reaching a macro-average F1-score of 0.74, demonstrating its efficacy in detecting hate speech in Devanagari script languages. However, the model we submitted achieved a macro-average F1-score of 0.73, securing 13th place in the subtask.
%U https://aclanthology.org/2025.chipsal-1.28/
%P 260-266
Markdown (Informal)
[CUET_HateShield@NLU of Devanagari Script Languages 2025: Transformer-Based Hate Speech Detection in Devanagari Script Languages](https://aclanthology.org/2025.chipsal-1.28/) (Aodhora et al., CHiPSAL 2025)
ACL