@inproceedings{rashfi-etal-2025-id4fusion,
title = "{ID}4{F}usion@{CASE} 2025: A Multimodal Approach to Hate Speech Detection in Text-Embedded Memes Using ensemble Transformer based approach",
author = "Rashfi, Tabassum Basher and
Shawon, Md. Tanvir Ahammed and
Mia, Md. Ayon and
Khan, Muhammad Ibrahim",
editor = {H{\"u}rriyeto{\u{g}}lu, Ali and
Tanev, Hristo and
Thapa, Surendrabikram},
booktitle = "Proceedings of the 8th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Texts",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.case-1.17/",
pages = "139--145",
abstract = "Identification of hate speech in images with text is a complicated task in the scope of online content moderation, especially when such talk penetrates into the spheres of humor and critical societal topics. This paper deals with Subtask A of the Shared Task on Multimodal Hate, Humor, and Stance Detection in Marginalized Movement@CASE2025. This task is binary classification over whether or not hate speech exists in image contents, and it advances as Hate versus No Hate. To meet this goal, we present a new multimodal architecture that blends the textual and visual features to reach effective classification. In the textual aspect, we have fine-tuned two state-of-the-art transformer models, which are RoBERTa and HateBERT, to extract linguistic clues of hate speech. The image encoder contains both the EfficientNetB7 and a Vision Transformer (ViT) model, which were found to work well in retrieving image-related details. The predictions made by each modality are then merged through an ensemble mechanism, with the last estimate being a weighted average of the text- and image-based scores. The resulting model produces a desirable F1- score metric of 0.7868, which is ranked 10 among the total number of systems, thus becoming a clear indicator of the success of multimodal combination in addressing the complex issue of self-identifying the hate speech in text-embedded images."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rashfi-etal-2025-id4fusion">
<titleInfo>
<title>ID4Fusion@CASE 2025: A Multimodal Approach to Hate Speech Detection in Text-Embedded Memes Using ensemble Transformer based approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tabassum</namePart>
<namePart type="given">Basher</namePart>
<namePart type="family">Rashfi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Tanvir</namePart>
<namePart type="given">Ahammed</namePart>
<namePart type="family">Shawon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Ayon</namePart>
<namePart type="family">Mia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Texts</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">Hristo</namePart>
<namePart type="family">Tanev</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>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Identification of hate speech in images with text is a complicated task in the scope of online content moderation, especially when such talk penetrates into the spheres of humor and critical societal topics. This paper deals with Subtask A of the Shared Task on Multimodal Hate, Humor, and Stance Detection in Marginalized Movement@CASE2025. This task is binary classification over whether or not hate speech exists in image contents, and it advances as Hate versus No Hate. To meet this goal, we present a new multimodal architecture that blends the textual and visual features to reach effective classification. In the textual aspect, we have fine-tuned two state-of-the-art transformer models, which are RoBERTa and HateBERT, to extract linguistic clues of hate speech. The image encoder contains both the EfficientNetB7 and a Vision Transformer (ViT) model, which were found to work well in retrieving image-related details. The predictions made by each modality are then merged through an ensemble mechanism, with the last estimate being a weighted average of the text- and image-based scores. The resulting model produces a desirable F1- score metric of 0.7868, which is ranked 10 among the total number of systems, thus becoming a clear indicator of the success of multimodal combination in addressing the complex issue of self-identifying the hate speech in text-embedded images.</abstract>
<identifier type="citekey">rashfi-etal-2025-id4fusion</identifier>
<location>
<url>https://aclanthology.org/2025.case-1.17/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>139</start>
<end>145</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ID4Fusion@CASE 2025: A Multimodal Approach to Hate Speech Detection in Text-Embedded Memes Using ensemble Transformer based approach
%A Rashfi, Tabassum Basher
%A Shawon, Md. Tanvir Ahammed
%A Mia, Md. Ayon
%A Khan, Muhammad Ibrahim
%Y Hürriyetoğlu, Ali
%Y Tanev, Hristo
%Y Thapa, Surendrabikram
%S Proceedings of the 8th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Texts
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F rashfi-etal-2025-id4fusion
%X Identification of hate speech in images with text is a complicated task in the scope of online content moderation, especially when such talk penetrates into the spheres of humor and critical societal topics. This paper deals with Subtask A of the Shared Task on Multimodal Hate, Humor, and Stance Detection in Marginalized Movement@CASE2025. This task is binary classification over whether or not hate speech exists in image contents, and it advances as Hate versus No Hate. To meet this goal, we present a new multimodal architecture that blends the textual and visual features to reach effective classification. In the textual aspect, we have fine-tuned two state-of-the-art transformer models, which are RoBERTa and HateBERT, to extract linguistic clues of hate speech. The image encoder contains both the EfficientNetB7 and a Vision Transformer (ViT) model, which were found to work well in retrieving image-related details. The predictions made by each modality are then merged through an ensemble mechanism, with the last estimate being a weighted average of the text- and image-based scores. The resulting model produces a desirable F1- score metric of 0.7868, which is ranked 10 among the total number of systems, thus becoming a clear indicator of the success of multimodal combination in addressing the complex issue of self-identifying the hate speech in text-embedded images.
%U https://aclanthology.org/2025.case-1.17/
%P 139-145
Markdown (Informal)
[ID4Fusion@CASE 2025: A Multimodal Approach to Hate Speech Detection in Text-Embedded Memes Using ensemble Transformer based approach](https://aclanthology.org/2025.case-1.17/) (Rashfi et al., CASE 2025)
ACL