@inproceedings{shanto-etal-2025-mdc3,
title = "{MDC}$^3$: A Novel Multimodal Dataset for Commercial Content Classification in {B}engali",
author = "Shanto, Anik Mahmud and
Priya, Mst. Sanjida Jamal and
Tamim, Fahim Shakil and
Hoque, Mohammed Moshiul",
editor = "Ebrahimi, Abteen and
Haider, Samar and
Liu, Emmy and
Haider, Sammar and
Leonor Pacheco, Maria and
Wein, Shira",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
month = apr,
year = "2025",
address = "Albuquerque, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-srw.31/",
doi = "10.18653/v1/2025.naacl-srw.31",
pages = "311--320",
ISBN = "979-8-89176-192-6",
abstract = "Identifying commercial posts in resource-constrained languages among diverse and unstructured content remains a significant challenge for automatic text classification tasks. To address this, this work introduces a novel dataset named MDC$^3$ (Multimodal Dataset for Commercial Content Classification), comprising 5,007 annotated Bengali social media posts classified as commercial and noncommercial. A comprehensive annotation guideline accompanying the dataset is included to aid future dataset creation in resource-constrained languages. Furthermore, we performed extensive experiments on MDC$^3$ considering both unimodal and multimodal domains. Specifically, the late fusion of textual (mBERT) and visual (ViT) models (i.e., ViT+mBERT) achieves the highest F1 score of 90.91, significantly surpassing other baselines."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shanto-etal-2025-mdc3">
<titleInfo>
<title>MDC³: A Novel Multimodal Dataset for Commercial Content Classification in Bengali</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anik</namePart>
<namePart type="given">Mahmud</namePart>
<namePart type="family">Shanto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mst.</namePart>
<namePart type="given">Sanjida</namePart>
<namePart type="given">Jamal</namePart>
<namePart type="family">Priya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fahim</namePart>
<namePart type="given">Shakil</namePart>
<namePart type="family">Tamim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="given">Moshiul</namePart>
<namePart type="family">Hoque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abteen</namePart>
<namePart type="family">Ebrahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmy</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sammar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Leonor Pacheco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shira</namePart>
<namePart type="family">Wein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-192-6</identifier>
</relatedItem>
<abstract>Identifying commercial posts in resource-constrained languages among diverse and unstructured content remains a significant challenge for automatic text classification tasks. To address this, this work introduces a novel dataset named MDC³ (Multimodal Dataset for Commercial Content Classification), comprising 5,007 annotated Bengali social media posts classified as commercial and noncommercial. A comprehensive annotation guideline accompanying the dataset is included to aid future dataset creation in resource-constrained languages. Furthermore, we performed extensive experiments on MDC³ considering both unimodal and multimodal domains. Specifically, the late fusion of textual (mBERT) and visual (ViT) models (i.e., ViT+mBERT) achieves the highest F1 score of 90.91, significantly surpassing other baselines.</abstract>
<identifier type="citekey">shanto-etal-2025-mdc3</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-srw.31</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-srw.31/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>311</start>
<end>320</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MDC³: A Novel Multimodal Dataset for Commercial Content Classification in Bengali
%A Shanto, Anik Mahmud
%A Priya, Mst. Sanjida Jamal
%A Tamim, Fahim Shakil
%A Hoque, Mohammed Moshiul
%Y Ebrahimi, Abteen
%Y Haider, Samar
%Y Liu, Emmy
%Y Haider, Sammar
%Y Leonor Pacheco, Maria
%Y Wein, Shira
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, USA
%@ 979-8-89176-192-6
%F shanto-etal-2025-mdc3
%X Identifying commercial posts in resource-constrained languages among diverse and unstructured content remains a significant challenge for automatic text classification tasks. To address this, this work introduces a novel dataset named MDC³ (Multimodal Dataset for Commercial Content Classification), comprising 5,007 annotated Bengali social media posts classified as commercial and noncommercial. A comprehensive annotation guideline accompanying the dataset is included to aid future dataset creation in resource-constrained languages. Furthermore, we performed extensive experiments on MDC³ considering both unimodal and multimodal domains. Specifically, the late fusion of textual (mBERT) and visual (ViT) models (i.e., ViT+mBERT) achieves the highest F1 score of 90.91, significantly surpassing other baselines.
%R 10.18653/v1/2025.naacl-srw.31
%U https://aclanthology.org/2025.naacl-srw.31/
%U https://doi.org/10.18653/v1/2025.naacl-srw.31
%P 311-320
Markdown (Informal)
[MDC3: A Novel Multimodal Dataset for Commercial Content Classification in Bengali](https://aclanthology.org/2025.naacl-srw.31/) (Shanto et al., NAACL 2025)
ACL
- Anik Mahmud Shanto, Mst. Sanjida Jamal Priya, Fahim Shakil Tamim, and Mohammed Moshiul Hoque. 2025. MDC3: A Novel Multimodal Dataset for Commercial Content Classification in Bengali. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop), pages 311–320, Albuquerque, USA. Association for Computational Linguistics.