@inproceedings{acharya-etal-2026-linus,
title = "Linus@{EEUCA} 2026: Multimodal and Text-Only Approaches to Vaccine-Critical Meme Detection.",
author = "Acharya, Darwin and
Saud, Shiv Ram and
Regmi, Sunil",
editor = {H{\"u}rriyeto{\u{g}}lu, Ali and
Thapa, Surendrabikram and
Tanev, Hristo},
booktitle = "Proceedings of the 9th Workshop on Event Extraction and Understanding: Challenges and Applications ({EEUCA} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eeuca-1.25/",
pages = "223--232",
ISBN = "979-8-89176-402-6",
abstract = "In this paper, we describe our participation in the Shared Task on Multimodal Identification of Vaccine Critical Content on Social Media (VaxMeme) of EEUCA 2026, a satellite of ACL 2026. We tackle the classification of Twitter-based vaccine memes into anti-vaccine, neutral, and pro-vaccine categories using the VaxMeme dataset with 8,195 train, 1,024 val, and 1,025 test samples. We experiment with two different architecture families: (i) Multimodal hybrids: CLIP ViT-B/32 for images + BERT-based models for texts (BERT-base-uncased, ModernBERT) with late fusion strategy based on concatenation of L2-normalized feature vectors and (ii) Text-only: pre-trained models for texts (BERT-base-uncased, RoBERTa-base, ModernBERT-base, DistilBERT-base, Deberta-v3-base) for post{\_}text. In both cases, we use a three-layer feed-forward network with GELU activation for classification. We use class-weighted cross-entropy loss, differential learning rates, AdamW optimizer, gradient accumulation, OneCycleLR scheduler, and early stopping on the val set for optimization. Data augmentation is applied for the multimodal CLIP-based approach only. The winning approach among those tested is the text-only BERT-base-uncased with a macro-F1 of 0.8102 which is ahead of the performance of the CLIP + BERT-base hybrid model, which achieves a test macro-F1 of 0.7603."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="acharya-etal-2026-linus">
<titleInfo>
<title>Linus@EEUCA 2026: Multimodal and Text-Only Approaches to Vaccine-Critical Meme Detection.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Darwin</namePart>
<namePart type="family">Acharya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiv</namePart>
<namePart type="given">Ram</namePart>
<namePart type="family">Saud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunil</namePart>
<namePart type="family">Regmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th Workshop on Event Extraction and Understanding: Challenges and Applications (EEUCA 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Hürriyetoğlu</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>
<name type="personal">
<namePart type="given">Hristo</namePart>
<namePart type="family">Tanev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-402-6</identifier>
</relatedItem>
<abstract>In this paper, we describe our participation in the Shared Task on Multimodal Identification of Vaccine Critical Content on Social Media (VaxMeme) of EEUCA 2026, a satellite of ACL 2026. We tackle the classification of Twitter-based vaccine memes into anti-vaccine, neutral, and pro-vaccine categories using the VaxMeme dataset with 8,195 train, 1,024 val, and 1,025 test samples. We experiment with two different architecture families: (i) Multimodal hybrids: CLIP ViT-B/32 for images + BERT-based models for texts (BERT-base-uncased, ModernBERT) with late fusion strategy based on concatenation of L2-normalized feature vectors and (ii) Text-only: pre-trained models for texts (BERT-base-uncased, RoBERTa-base, ModernBERT-base, DistilBERT-base, Deberta-v3-base) for post_text. In both cases, we use a three-layer feed-forward network with GELU activation for classification. We use class-weighted cross-entropy loss, differential learning rates, AdamW optimizer, gradient accumulation, OneCycleLR scheduler, and early stopping on the val set for optimization. Data augmentation is applied for the multimodal CLIP-based approach only. The winning approach among those tested is the text-only BERT-base-uncased with a macro-F1 of 0.8102 which is ahead of the performance of the CLIP + BERT-base hybrid model, which achieves a test macro-F1 of 0.7603.</abstract>
<identifier type="citekey">acharya-etal-2026-linus</identifier>
<location>
<url>https://aclanthology.org/2026.eeuca-1.25/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>223</start>
<end>232</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Linus@EEUCA 2026: Multimodal and Text-Only Approaches to Vaccine-Critical Meme Detection.
%A Acharya, Darwin
%A Saud, Shiv Ram
%A Regmi, Sunil
%Y Hürriyetoğlu, Ali
%Y Thapa, Surendrabikram
%Y Tanev, Hristo
%S Proceedings of the 9th Workshop on Event Extraction and Understanding: Challenges and Applications (EEUCA 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-402-6
%F acharya-etal-2026-linus
%X In this paper, we describe our participation in the Shared Task on Multimodal Identification of Vaccine Critical Content on Social Media (VaxMeme) of EEUCA 2026, a satellite of ACL 2026. We tackle the classification of Twitter-based vaccine memes into anti-vaccine, neutral, and pro-vaccine categories using the VaxMeme dataset with 8,195 train, 1,024 val, and 1,025 test samples. We experiment with two different architecture families: (i) Multimodal hybrids: CLIP ViT-B/32 for images + BERT-based models for texts (BERT-base-uncased, ModernBERT) with late fusion strategy based on concatenation of L2-normalized feature vectors and (ii) Text-only: pre-trained models for texts (BERT-base-uncased, RoBERTa-base, ModernBERT-base, DistilBERT-base, Deberta-v3-base) for post_text. In both cases, we use a three-layer feed-forward network with GELU activation for classification. We use class-weighted cross-entropy loss, differential learning rates, AdamW optimizer, gradient accumulation, OneCycleLR scheduler, and early stopping on the val set for optimization. Data augmentation is applied for the multimodal CLIP-based approach only. The winning approach among those tested is the text-only BERT-base-uncased with a macro-F1 of 0.8102 which is ahead of the performance of the CLIP + BERT-base hybrid model, which achieves a test macro-F1 of 0.7603.
%U https://aclanthology.org/2026.eeuca-1.25/
%P 223-232
Markdown (Informal)
[Linus@EEUCA 2026: Multimodal and Text-Only Approaches to Vaccine-Critical Meme Detection.](https://aclanthology.org/2026.eeuca-1.25/) (Acharya et al., EEUCA 2026)
ACL