@inproceedings{thapa-etal-2026-multimodal-hate,
title = "Multimodal Hate and Sentiment Understanding in Low-Resource Text-Embedded Images for Online Safety and Digital Well-being",
author = "Thapa, Surendrabikram and
Shiwakoti, Shuvam and
Shah, Siddhant Bikram and
Rauniyar, Kritesh and
Thapa, Laxmi and
Adhikari, Surabhi and
Johnson, Kristina T and
Sarveswaran, Kengatharaiyer and
Bal, Bal Krishna and
Naseem, Usman",
editor = "Sarveswaran, Kengatharaiyer and
Vaidya, Ashwini",
booktitle = "Proceedings of the Second workshop on Challenges in Processing {S}outh {A}sian Languages ({CH}i{PSAL}2026)",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.chipsal-1.21/",
doi = "10.63317/3rhxrpvoi74j",
pages = "219--228",
abstract = "This paper presents an overview of the Shared Task on Multimodal Hate and Sentiment Understanding in Low-Resource Memes, organized as part of the Second Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2026) at LREC 2026. The task addresses automated content understanding in low-resource settings by focusing on monolingual Nepali memes written in Devanagari script. Built upon the NeMeme dataset, the task comprises two subtasks: (1) binary hate speech detection and (2) three-class sentiment analysis. The competition attracted 23 teams for hate detection and 13 teams for sentiment analysis. Participating teams employed diverse strategies, including late-fusion multimodal architectures combining multilingual text encoders with vision models, caption-based approaches using large vision-language models, and ensemble techniques. The top-performing system achieved macro-F1 scores of 80.52{\%} on hate detection and 68.81{\%} on sentiment analysis using a late-fusion hybrid architecture with discriminative learning rates. Our analysis reveals that multimodal fusion consistently outperforms unimodal baselines, sentiment analysis poses greater challenges than hate detection due to increased semantic nuance, and the scarcity of Devanagari-centric pretrained models remains a significant bottleneck. This shared task establishes a benchmark for multimodal understanding in low-resource South Asian languages and provides insights for developing inclusive content moderation systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="thapa-etal-2026-multimodal-hate">
<titleInfo>
<title>Multimodal Hate and Sentiment Understanding in Low-Resource Text-Embedded Images for Online Safety and Digital Well-being</title>
</titleInfo>
<name type="personal">
<namePart type="given">Surendrabikram</namePart>
<namePart type="family">Thapa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuvam</namePart>
<namePart type="family">Shiwakoti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddhant</namePart>
<namePart type="given">Bikram</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kritesh</namePart>
<namePart type="family">Rauniyar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laxmi</namePart>
<namePart type="family">Thapa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surabhi</namePart>
<namePart type="family">Adhikari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Johnson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kengatharaiyer</namePart>
<namePart type="family">Sarveswaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bal</namePart>
<namePart type="given">Krishna</namePart>
<namePart type="family">Bal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Usman</namePart>
<namePart type="family">Naseem</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 Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026)</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>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents an overview of the Shared Task on Multimodal Hate and Sentiment Understanding in Low-Resource Memes, organized as part of the Second Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2026) at LREC 2026. The task addresses automated content understanding in low-resource settings by focusing on monolingual Nepali memes written in Devanagari script. Built upon the NeMeme dataset, the task comprises two subtasks: (1) binary hate speech detection and (2) three-class sentiment analysis. The competition attracted 23 teams for hate detection and 13 teams for sentiment analysis. Participating teams employed diverse strategies, including late-fusion multimodal architectures combining multilingual text encoders with vision models, caption-based approaches using large vision-language models, and ensemble techniques. The top-performing system achieved macro-F1 scores of 80.52% on hate detection and 68.81% on sentiment analysis using a late-fusion hybrid architecture with discriminative learning rates. Our analysis reveals that multimodal fusion consistently outperforms unimodal baselines, sentiment analysis poses greater challenges than hate detection due to increased semantic nuance, and the scarcity of Devanagari-centric pretrained models remains a significant bottleneck. This shared task establishes a benchmark for multimodal understanding in low-resource South Asian languages and provides insights for developing inclusive content moderation systems.</abstract>
<identifier type="citekey">thapa-etal-2026-multimodal-hate</identifier>
<identifier type="doi">10.63317/3rhxrpvoi74j</identifier>
<location>
<url>https://aclanthology.org/2026.chipsal-1.21/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>219</start>
<end>228</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multimodal Hate and Sentiment Understanding in Low-Resource Text-Embedded Images for Online Safety and Digital Well-being
%A Thapa, Surendrabikram
%A Shiwakoti, Shuvam
%A Shah, Siddhant Bikram
%A Rauniyar, Kritesh
%A Thapa, Laxmi
%A Adhikari, Surabhi
%A Johnson, Kristina T.
%A Sarveswaran, Kengatharaiyer
%A Bal, Bal Krishna
%A Naseem, Usman
%Y Sarveswaran, Kengatharaiyer
%Y Vaidya, Ashwini
%S Proceedings of the Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026)
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma de Mallorca, Spain
%F thapa-etal-2026-multimodal-hate
%X This paper presents an overview of the Shared Task on Multimodal Hate and Sentiment Understanding in Low-Resource Memes, organized as part of the Second Workshop on Challenges in Processing South Asian Languages (CHiPSAL 2026) at LREC 2026. The task addresses automated content understanding in low-resource settings by focusing on monolingual Nepali memes written in Devanagari script. Built upon the NeMeme dataset, the task comprises two subtasks: (1) binary hate speech detection and (2) three-class sentiment analysis. The competition attracted 23 teams for hate detection and 13 teams for sentiment analysis. Participating teams employed diverse strategies, including late-fusion multimodal architectures combining multilingual text encoders with vision models, caption-based approaches using large vision-language models, and ensemble techniques. The top-performing system achieved macro-F1 scores of 80.52% on hate detection and 68.81% on sentiment analysis using a late-fusion hybrid architecture with discriminative learning rates. Our analysis reveals that multimodal fusion consistently outperforms unimodal baselines, sentiment analysis poses greater challenges than hate detection due to increased semantic nuance, and the scarcity of Devanagari-centric pretrained models remains a significant bottleneck. This shared task establishes a benchmark for multimodal understanding in low-resource South Asian languages and provides insights for developing inclusive content moderation systems.
%R 10.63317/3rhxrpvoi74j
%U https://aclanthology.org/2026.chipsal-1.21/
%U https://doi.org/10.63317/3rhxrpvoi74j
%P 219-228
Markdown (Informal)
[Multimodal Hate and Sentiment Understanding in Low-Resource Text-Embedded Images for Online Safety and Digital Well-being](https://aclanthology.org/2026.chipsal-1.21/) (Thapa et al., CHiPSAL 2026)
ACL
- Surendrabikram Thapa, Shuvam Shiwakoti, Siddhant Bikram Shah, Kritesh Rauniyar, Laxmi Thapa, Surabhi Adhikari, Kristina T Johnson, Kengatharaiyer Sarveswaran, Bal Krishna Bal, and Usman Naseem. 2026. Multimodal Hate and Sentiment Understanding in Low-Resource Text-Embedded Images for Online Safety and Digital Well-being. In Proceedings of the Second workshop on Challenges in Processing South Asian Languages (CHiPSAL2026), pages 219–228, Palma de Mallorca, Spain. ELRA Language Resources Association (ELRA).