@inproceedings{aldabbas-etal-2025-multiprop,
title = "{M}ulti{P}rop Framework: Ensemble Models for Enhanced Cross-Lingual Propaganda Detection in Social Media and News using Data Augmentation, Text Segmentation, and Meta-Learning",
author = "Aldabbas, Farizeh and
Ashraf, Shaina and
Sifa, Rafet and
Flek, Lucie",
editor = "El-Haj, Mo",
booktitle = "Proceedings of the 1st Workshop on NLP for Languages Using Arabic Script",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.abjadnlp-1.2/",
pages = "7--22",
abstract = "Propaganda, a pervasive tool for influenc- ing public opinion, demands robust auto- mated detection systems, particularly for under- resourced languages. Current efforts largely focus on well-resourced languages like English, leaving significant gaps in languages such as Arabic. This research addresses these gaps by introducing MultiProp Framework, a cross- lingual meta-learning framework designed to enhance propaganda detection across multiple languages, including Arabic, German, Italian, French and English. We constructed a mul- tilingual dataset using data translation tech- niques, beginning with Arabic data from PTC and WANLP shared tasks, and expanded it with translations into German Italian and French, further enriched by the SemEval23 dataset. Our proposed framework encompasses three distinct models: MultiProp-Baseline, which combines ensembles of pre-trained models such as GPT-2, mBART, and XLM-RoBERTa; MultiProp-ML, designed to handle languages with minimal or no training data by utiliz- ing advanced meta-learning techniques; and MultiProp-Chunk, which overcomes the chal- lenges of processing longer texts that exceed the token limits of pre-trained models. To- gether, they deliver superior performance com- pared to state-of-the-art methods, representing a significant advancement in the field of cross- lingual propaganda detection."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aldabbas-etal-2025-multiprop">
<titleInfo>
<title>MultiProp Framework: Ensemble Models for Enhanced Cross-Lingual Propaganda Detection in Social Media and News using Data Augmentation, Text Segmentation, and Meta-Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Farizeh</namePart>
<namePart type="family">Aldabbas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaina</namePart>
<namePart type="family">Ashraf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafet</namePart>
<namePart type="family">Sifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucie</namePart>
<namePart type="family">Flek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on NLP for Languages Using Arabic Script</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mo</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Propaganda, a pervasive tool for influenc- ing public opinion, demands robust auto- mated detection systems, particularly for under- resourced languages. Current efforts largely focus on well-resourced languages like English, leaving significant gaps in languages such as Arabic. This research addresses these gaps by introducing MultiProp Framework, a cross- lingual meta-learning framework designed to enhance propaganda detection across multiple languages, including Arabic, German, Italian, French and English. We constructed a mul- tilingual dataset using data translation tech- niques, beginning with Arabic data from PTC and WANLP shared tasks, and expanded it with translations into German Italian and French, further enriched by the SemEval23 dataset. Our proposed framework encompasses three distinct models: MultiProp-Baseline, which combines ensembles of pre-trained models such as GPT-2, mBART, and XLM-RoBERTa; MultiProp-ML, designed to handle languages with minimal or no training data by utiliz- ing advanced meta-learning techniques; and MultiProp-Chunk, which overcomes the chal- lenges of processing longer texts that exceed the token limits of pre-trained models. To- gether, they deliver superior performance com- pared to state-of-the-art methods, representing a significant advancement in the field of cross- lingual propaganda detection.</abstract>
<identifier type="citekey">aldabbas-etal-2025-multiprop</identifier>
<location>
<url>https://aclanthology.org/2025.abjadnlp-1.2/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>7</start>
<end>22</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MultiProp Framework: Ensemble Models for Enhanced Cross-Lingual Propaganda Detection in Social Media and News using Data Augmentation, Text Segmentation, and Meta-Learning
%A Aldabbas, Farizeh
%A Ashraf, Shaina
%A Sifa, Rafet
%A Flek, Lucie
%Y El-Haj, Mo
%S Proceedings of the 1st Workshop on NLP for Languages Using Arabic Script
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F aldabbas-etal-2025-multiprop
%X Propaganda, a pervasive tool for influenc- ing public opinion, demands robust auto- mated detection systems, particularly for under- resourced languages. Current efforts largely focus on well-resourced languages like English, leaving significant gaps in languages such as Arabic. This research addresses these gaps by introducing MultiProp Framework, a cross- lingual meta-learning framework designed to enhance propaganda detection across multiple languages, including Arabic, German, Italian, French and English. We constructed a mul- tilingual dataset using data translation tech- niques, beginning with Arabic data from PTC and WANLP shared tasks, and expanded it with translations into German Italian and French, further enriched by the SemEval23 dataset. Our proposed framework encompasses three distinct models: MultiProp-Baseline, which combines ensembles of pre-trained models such as GPT-2, mBART, and XLM-RoBERTa; MultiProp-ML, designed to handle languages with minimal or no training data by utiliz- ing advanced meta-learning techniques; and MultiProp-Chunk, which overcomes the chal- lenges of processing longer texts that exceed the token limits of pre-trained models. To- gether, they deliver superior performance com- pared to state-of-the-art methods, representing a significant advancement in the field of cross- lingual propaganda detection.
%U https://aclanthology.org/2025.abjadnlp-1.2/
%P 7-22
Markdown (Informal)
[MultiProp Framework: Ensemble Models for Enhanced Cross-Lingual Propaganda Detection in Social Media and News using Data Augmentation, Text Segmentation, and Meta-Learning](https://aclanthology.org/2025.abjadnlp-1.2/) (Aldabbas et al., AbjadNLP 2025)
ACL