@inproceedings{maity-etal-2024-toxvidlm,
title = "{T}ox{V}id{LM}: A Multimodal Framework for Toxicity Detection in Code-Mixed Videos",
author = "Maity, Krishanu and
Poornash, A.s. and
Saha, Sriparna and
Bhattacharyya, Pushpak",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.663",
doi = "10.18653/v1/2024.findings-acl.663",
pages = "11130--11142",
abstract = "In an era of rapidly evolving internet technology, the surge in multimodal content, including videos, has expanded the horizons of online communication. However, the detection of toxic content in this diverse landscape, particularly in low-resource code-mixed languages, remains a critical challenge. While substantial research has addressed toxic content detection in textual data, the realm of video content, especially in non-English languages, has been relatively underexplored. This paper addresses this research gap by introducing a benchmark dataset, the first of its kind, consisting of 931 videos with 4021 code-mixed Hindi-English utterances collected from YouTube. Each utterance within this dataset has been meticulously annotated for toxicity, severity, and sentiment labels. We have developed an advanced Multimodal Multitask framework built for Toxicity detection in Video Content by leveraging Language Models (LMs), crafted for the primary objective along with the additional tasks of conducting sentiment and severity analysis. ToxVidLM incorporates three key modules {--} the Encoder module, Cross-Modal Synchronization module, and Multitask module {--} crafting a generic multimodal LM customized for intricate video classification tasks. Our experiments reveal that incorporating multiple modalities from the videos substantially enhances the performance of toxic content detection by achieving an Accuracy and Weighted F1 score of 94.29{\%} and 94.35{\%}, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maity-etal-2024-toxvidlm">
<titleInfo>
<title>ToxVidLM: A Multimodal Framework for Toxicity Detection in Code-Mixed Videos</title>
</titleInfo>
<name type="personal">
<namePart type="given">Krishanu</namePart>
<namePart type="family">Maity</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A.s.</namePart>
<namePart type="family">Poornash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sriparna</namePart>
<namePart type="family">Saha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</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>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In an era of rapidly evolving internet technology, the surge in multimodal content, including videos, has expanded the horizons of online communication. However, the detection of toxic content in this diverse landscape, particularly in low-resource code-mixed languages, remains a critical challenge. While substantial research has addressed toxic content detection in textual data, the realm of video content, especially in non-English languages, has been relatively underexplored. This paper addresses this research gap by introducing a benchmark dataset, the first of its kind, consisting of 931 videos with 4021 code-mixed Hindi-English utterances collected from YouTube. Each utterance within this dataset has been meticulously annotated for toxicity, severity, and sentiment labels. We have developed an advanced Multimodal Multitask framework built for Toxicity detection in Video Content by leveraging Language Models (LMs), crafted for the primary objective along with the additional tasks of conducting sentiment and severity analysis. ToxVidLM incorporates three key modules – the Encoder module, Cross-Modal Synchronization module, and Multitask module – crafting a generic multimodal LM customized for intricate video classification tasks. Our experiments reveal that incorporating multiple modalities from the videos substantially enhances the performance of toxic content detection by achieving an Accuracy and Weighted F1 score of 94.29% and 94.35%, respectively.</abstract>
<identifier type="citekey">maity-etal-2024-toxvidlm</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.663</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.663</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>11130</start>
<end>11142</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ToxVidLM: A Multimodal Framework for Toxicity Detection in Code-Mixed Videos
%A Maity, Krishanu
%A Poornash, A.s.
%A Saha, Sriparna
%A Bhattacharyya, Pushpak
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F maity-etal-2024-toxvidlm
%X In an era of rapidly evolving internet technology, the surge in multimodal content, including videos, has expanded the horizons of online communication. However, the detection of toxic content in this diverse landscape, particularly in low-resource code-mixed languages, remains a critical challenge. While substantial research has addressed toxic content detection in textual data, the realm of video content, especially in non-English languages, has been relatively underexplored. This paper addresses this research gap by introducing a benchmark dataset, the first of its kind, consisting of 931 videos with 4021 code-mixed Hindi-English utterances collected from YouTube. Each utterance within this dataset has been meticulously annotated for toxicity, severity, and sentiment labels. We have developed an advanced Multimodal Multitask framework built for Toxicity detection in Video Content by leveraging Language Models (LMs), crafted for the primary objective along with the additional tasks of conducting sentiment and severity analysis. ToxVidLM incorporates three key modules – the Encoder module, Cross-Modal Synchronization module, and Multitask module – crafting a generic multimodal LM customized for intricate video classification tasks. Our experiments reveal that incorporating multiple modalities from the videos substantially enhances the performance of toxic content detection by achieving an Accuracy and Weighted F1 score of 94.29% and 94.35%, respectively.
%R 10.18653/v1/2024.findings-acl.663
%U https://aclanthology.org/2024.findings-acl.663
%U https://doi.org/10.18653/v1/2024.findings-acl.663
%P 11130-11142
Markdown (Informal)
[ToxVidLM: A Multimodal Framework for Toxicity Detection in Code-Mixed Videos](https://aclanthology.org/2024.findings-acl.663) (Maity et al., Findings 2024)
ACL