@inproceedings{hossain-etal-2025-semanticcuetsync,
title = "{S}emantic{C}uet{S}ync@{D}ravidian{L}ang{T}ech 2025: Multimodal Fusion for Hate Speech Detection - A Transformer Based Approach with Cross-Modal Attention",
author = "Hossain, Md. Sajjad and
Shohan, Symom Hossain and
Paran, Ashraful Islam and
Hossain, Jawad and
Hoque, Mohammed Moshiul",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Madasamy, Anand Kumar and
Thavareesan, Sajeetha and
Sherly, Elizabeth and
Rajiakodi, Saranya and
Palani, Balasubramanian and
Subramanian, Malliga and
Cn, Subalalitha and
Chinnappa, Dhivya",
booktitle = "Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages",
month = may,
year = "2025",
address = "Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.dravidianlangtech-1.86/",
doi = "10.18653/v1/2025.dravidianlangtech-1.86",
pages = "489--495",
ISBN = "979-8-89176-228-2",
abstract = "The rise of social media has significantly facilitated the rapid spread of hate speech. Detecting hate speech for content moderation is challenging, especially in low-resource languages (LRLs) like Telugu. Although some progress has been noticed in hate speech detection in Telegu concerning unimodal (text or image) in recent years, there is a lack of research on hate speech detection based on multimodal content detection (specifically using audio and text). In this regard, DravidianLangTech has arranged a shared task to address this challenge. This work explored three machine learning (ML), three deep learning (DL), and seven transformer-based models that integrate text and audio modalities using cross-modal attention for hate speech detection. The evaluation results demonstrate that mBERT achieved the highest F-1 score of 49.68{\%} using text. However, the proposed multimodal attention-based approach with Whisper-small+TeluguBERT-3 achieved an F-1 score of 43 68{\%}, which helped us achieve a rank of 3rd in the shared task competition."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hossain-etal-2025-semanticcuetsync">
<titleInfo>
<title>SemanticCuetSync@DravidianLangTech 2025: Multimodal Fusion for Hate Speech Detection - A Transformer Based Approach with Cross-Modal Attention</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Sajjad</namePart>
<namePart type="family">Hossain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Symom</namePart>
<namePart type="given">Hossain</namePart>
<namePart type="family">Shohan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashraful</namePart>
<namePart type="given">Islam</namePart>
<namePart type="family">Paran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jawad</namePart>
<namePart type="family">Hossain</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>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruba</namePart>
<namePart type="family">Priyadharshini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anand</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Madasamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sajeetha</namePart>
<namePart type="family">Thavareesan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Sherly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saranya</namePart>
<namePart type="family">Rajiakodi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Balasubramanian</namePart>
<namePart type="family">Palani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malliga</namePart>
<namePart type="family">Subramanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subalalitha</namePart>
<namePart type="family">Cn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhivya</namePart>
<namePart type="family">Chinnappa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-228-2</identifier>
</relatedItem>
<abstract>The rise of social media has significantly facilitated the rapid spread of hate speech. Detecting hate speech for content moderation is challenging, especially in low-resource languages (LRLs) like Telugu. Although some progress has been noticed in hate speech detection in Telegu concerning unimodal (text or image) in recent years, there is a lack of research on hate speech detection based on multimodal content detection (specifically using audio and text). In this regard, DravidianLangTech has arranged a shared task to address this challenge. This work explored three machine learning (ML), three deep learning (DL), and seven transformer-based models that integrate text and audio modalities using cross-modal attention for hate speech detection. The evaluation results demonstrate that mBERT achieved the highest F-1 score of 49.68% using text. However, the proposed multimodal attention-based approach with Whisper-small+TeluguBERT-3 achieved an F-1 score of 43 68%, which helped us achieve a rank of 3rd in the shared task competition.</abstract>
<identifier type="citekey">hossain-etal-2025-semanticcuetsync</identifier>
<identifier type="doi">10.18653/v1/2025.dravidianlangtech-1.86</identifier>
<location>
<url>https://aclanthology.org/2025.dravidianlangtech-1.86/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>489</start>
<end>495</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SemanticCuetSync@DravidianLangTech 2025: Multimodal Fusion for Hate Speech Detection - A Transformer Based Approach with Cross-Modal Attention
%A Hossain, Md. Sajjad
%A Shohan, Symom Hossain
%A Paran, Ashraful Islam
%A Hossain, Jawad
%A Hoque, Mohammed Moshiul
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Madasamy, Anand Kumar
%Y Thavareesan, Sajeetha
%Y Sherly, Elizabeth
%Y Rajiakodi, Saranya
%Y Palani, Balasubramanian
%Y Subramanian, Malliga
%Y Cn, Subalalitha
%Y Chinnappa, Dhivya
%S Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages
%D 2025
%8 May
%I Association for Computational Linguistics
%C Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico
%@ 979-8-89176-228-2
%F hossain-etal-2025-semanticcuetsync
%X The rise of social media has significantly facilitated the rapid spread of hate speech. Detecting hate speech for content moderation is challenging, especially in low-resource languages (LRLs) like Telugu. Although some progress has been noticed in hate speech detection in Telegu concerning unimodal (text or image) in recent years, there is a lack of research on hate speech detection based on multimodal content detection (specifically using audio and text). In this regard, DravidianLangTech has arranged a shared task to address this challenge. This work explored three machine learning (ML), three deep learning (DL), and seven transformer-based models that integrate text and audio modalities using cross-modal attention for hate speech detection. The evaluation results demonstrate that mBERT achieved the highest F-1 score of 49.68% using text. However, the proposed multimodal attention-based approach with Whisper-small+TeluguBERT-3 achieved an F-1 score of 43 68%, which helped us achieve a rank of 3rd in the shared task competition.
%R 10.18653/v1/2025.dravidianlangtech-1.86
%U https://aclanthology.org/2025.dravidianlangtech-1.86/
%U https://doi.org/10.18653/v1/2025.dravidianlangtech-1.86
%P 489-495
Markdown (Informal)
[SemanticCuetSync@DravidianLangTech 2025: Multimodal Fusion for Hate Speech Detection - A Transformer Based Approach with Cross-Modal Attention](https://aclanthology.org/2025.dravidianlangtech-1.86/) (Hossain et al., DravidianLangTech 2025)
ACL
- Md. Sajjad Hossain, Symom Hossain Shohan, Ashraful Islam Paran, Jawad Hossain, and Mohammed Moshiul Hoque. 2025. SemanticCuetSync@DravidianLangTech 2025: Multimodal Fusion for Hate Speech Detection - A Transformer Based Approach with Cross-Modal Attention. In Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, pages 489–495, Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico. Association for Computational Linguistics.