@inproceedings{ashraf-etal-2024-defakts-german,
title = "{D}e{F}akt{S}: A {G}erman Dataset for Fine-Grained Disinformation Detection through Social Media Framing",
author = "Ashraf, Shaina and
Bezzaoui, Isabel and
Andone, Ionut and
Markowetz, Alexander and
Fegert, Jonas and
Flek, Lucie",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.409",
pages = "4580--4591",
abstract = "In today{'}s rapidly evolving digital age, disinformation poses a significant threat to public sentiment and socio-political dynamics. To address this, we introduce a new dataset {``}DeFaktS{''}, designed to understand and counter disinformation within German media. Distinctively curated across various news topics, DeFaktS offers an unparalleled insight into the diverse facets of disinformation. Our dataset, containing 105,855 posts with 20,008 meticulously labeled tweets, serves as a rich platform for in-depth exploration of disinformation{'}s diverse characteristics. A key attribute that sets DeFaktS apart is, its fine-grain annotations based on polarized categories. Our annotation framework, grounded in the textual characteristics of news content, eliminates the need for external knowledge sources. Unlike most existing corpora that typically assign a singular global veracity value to news, our methodology seeks to annotate every structural component and semantic element of a news piece, ensuring a comprehensive and detailed understanding. In our experiments, we employed a mix of classical machine learning and advanced transformer-based models. The results underscored the potential of DeFaktS, with transformer models, especially the German variant of BERT, exhibiting pronounced effectiveness in both binary and fine-grained classifications.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ashraf-etal-2024-defakts-german">
<titleInfo>
<title>DeFaktS: A German Dataset for Fine-Grained Disinformation Detection through Social Media Framing</title>
</titleInfo>
<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">Isabel</namePart>
<namePart type="family">Bezzaoui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ionut</namePart>
<namePart type="family">Andone</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Markowetz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="family">Fegert</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>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In today’s rapidly evolving digital age, disinformation poses a significant threat to public sentiment and socio-political dynamics. To address this, we introduce a new dataset “DeFaktS”, designed to understand and counter disinformation within German media. Distinctively curated across various news topics, DeFaktS offers an unparalleled insight into the diverse facets of disinformation. Our dataset, containing 105,855 posts with 20,008 meticulously labeled tweets, serves as a rich platform for in-depth exploration of disinformation’s diverse characteristics. A key attribute that sets DeFaktS apart is, its fine-grain annotations based on polarized categories. Our annotation framework, grounded in the textual characteristics of news content, eliminates the need for external knowledge sources. Unlike most existing corpora that typically assign a singular global veracity value to news, our methodology seeks to annotate every structural component and semantic element of a news piece, ensuring a comprehensive and detailed understanding. In our experiments, we employed a mix of classical machine learning and advanced transformer-based models. The results underscored the potential of DeFaktS, with transformer models, especially the German variant of BERT, exhibiting pronounced effectiveness in both binary and fine-grained classifications.</abstract>
<identifier type="citekey">ashraf-etal-2024-defakts-german</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.409</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4580</start>
<end>4591</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DeFaktS: A German Dataset for Fine-Grained Disinformation Detection through Social Media Framing
%A Ashraf, Shaina
%A Bezzaoui, Isabel
%A Andone, Ionut
%A Markowetz, Alexander
%A Fegert, Jonas
%A Flek, Lucie
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F ashraf-etal-2024-defakts-german
%X In today’s rapidly evolving digital age, disinformation poses a significant threat to public sentiment and socio-political dynamics. To address this, we introduce a new dataset “DeFaktS”, designed to understand and counter disinformation within German media. Distinctively curated across various news topics, DeFaktS offers an unparalleled insight into the diverse facets of disinformation. Our dataset, containing 105,855 posts with 20,008 meticulously labeled tweets, serves as a rich platform for in-depth exploration of disinformation’s diverse characteristics. A key attribute that sets DeFaktS apart is, its fine-grain annotations based on polarized categories. Our annotation framework, grounded in the textual characteristics of news content, eliminates the need for external knowledge sources. Unlike most existing corpora that typically assign a singular global veracity value to news, our methodology seeks to annotate every structural component and semantic element of a news piece, ensuring a comprehensive and detailed understanding. In our experiments, we employed a mix of classical machine learning and advanced transformer-based models. The results underscored the potential of DeFaktS, with transformer models, especially the German variant of BERT, exhibiting pronounced effectiveness in both binary and fine-grained classifications.
%U https://aclanthology.org/2024.lrec-main.409
%P 4580-4591
Markdown (Informal)
[DeFaktS: A German Dataset for Fine-Grained Disinformation Detection through Social Media Framing](https://aclanthology.org/2024.lrec-main.409) (Ashraf et al., LREC-COLING 2024)
ACL