@inproceedings{rammohan-etal-2026-leveraging,
title = "Leveraging Semi-Supervised Learning for Multimodal Hate Speech Data Annotation and Detection",
author = {Rammohan, Rathi Adarshi and
Ren, Zhao and
Pucha{\l}a, Dominik and
{\'S}widerska, Aleksandra and
K{\"u}ster, Dennis and
Schultz, Tanja},
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.806/",
doi = "10.63317/4un2wjkpdn2m",
pages = "10266--10275",
abstract = "While the Internet and social media have fundamentally transformed our lives, they can also rapidly spread hate speech, i.e., derogatory statements targeting individuals or groups based on their immutable characteristics. Automatic detection systems could help limit this harmful phenomenon. However, the lack of large-scale annotated datasets remains a major bottleneck for developing better algorithms. In this work, we employ semi-supervised learning (SSL) to leverage the advantages of limited labeled data alongside large amounts of unlabeled data. We apply three SSL approaches, Fix-match, Full-match, and All-match learning, to enhance the performance of end-to-end pre-trained speech and text models for hate speech detection. Our findings indicate that SSL methods enhance the performance, achieving F1 scores of 0.851 on speech, 0.957 on text, and 0.959 with multimodal fusion. Furthermore, we analyze the impact of different weak augmentation strategies on labeled data and assess the quality of generated pseudo-labels to evaluate their potential use in data annotation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rammohan-etal-2026-leveraging">
<titleInfo>
<title>Leveraging Semi-Supervised Learning for Multimodal Hate Speech Data Annotation and Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rathi</namePart>
<namePart type="given">Adarshi</namePart>
<namePart type="family">Rammohan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhao</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dominik</namePart>
<namePart type="family">Puchała</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleksandra</namePart>
<namePart type="family">Świderska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dennis</namePart>
<namePart type="family">Küster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanja</namePart>
<namePart type="family">Schultz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While the Internet and social media have fundamentally transformed our lives, they can also rapidly spread hate speech, i.e., derogatory statements targeting individuals or groups based on their immutable characteristics. Automatic detection systems could help limit this harmful phenomenon. However, the lack of large-scale annotated datasets remains a major bottleneck for developing better algorithms. In this work, we employ semi-supervised learning (SSL) to leverage the advantages of limited labeled data alongside large amounts of unlabeled data. We apply three SSL approaches, Fix-match, Full-match, and All-match learning, to enhance the performance of end-to-end pre-trained speech and text models for hate speech detection. Our findings indicate that SSL methods enhance the performance, achieving F1 scores of 0.851 on speech, 0.957 on text, and 0.959 with multimodal fusion. Furthermore, we analyze the impact of different weak augmentation strategies on labeled data and assess the quality of generated pseudo-labels to evaluate their potential use in data annotation.</abstract>
<identifier type="citekey">rammohan-etal-2026-leveraging</identifier>
<identifier type="doi">10.63317/4un2wjkpdn2m</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.806/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>10266</start>
<end>10275</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Semi-Supervised Learning for Multimodal Hate Speech Data Annotation and Detection
%A Rammohan, Rathi Adarshi
%A Ren, Zhao
%A Puchała, Dominik
%A Świderska, Aleksandra
%A Küster, Dennis
%A Schultz, Tanja
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F rammohan-etal-2026-leveraging
%X While the Internet and social media have fundamentally transformed our lives, they can also rapidly spread hate speech, i.e., derogatory statements targeting individuals or groups based on their immutable characteristics. Automatic detection systems could help limit this harmful phenomenon. However, the lack of large-scale annotated datasets remains a major bottleneck for developing better algorithms. In this work, we employ semi-supervised learning (SSL) to leverage the advantages of limited labeled data alongside large amounts of unlabeled data. We apply three SSL approaches, Fix-match, Full-match, and All-match learning, to enhance the performance of end-to-end pre-trained speech and text models for hate speech detection. Our findings indicate that SSL methods enhance the performance, achieving F1 scores of 0.851 on speech, 0.957 on text, and 0.959 with multimodal fusion. Furthermore, we analyze the impact of different weak augmentation strategies on labeled data and assess the quality of generated pseudo-labels to evaluate their potential use in data annotation.
%R 10.63317/4un2wjkpdn2m
%U https://aclanthology.org/2026.lrec-1.806/
%U https://doi.org/10.63317/4un2wjkpdn2m
%P 10266-10275
Markdown (Informal)
[Leveraging Semi-Supervised Learning for Multimodal Hate Speech Data Annotation and Detection](https://aclanthology.org/2026.lrec-1.806/) (Rammohan et al., LREC 2026)
ACL