@inproceedings{dzienisiewicz-etal-2024-polygraph,
title = "{POL}ygraph: {P}olish Fake News Dataset",
author = "Dzienisiewicz, Daniel and
Grali{\'n}ski, Filip and
Jab{\l}o{\'n}ski, Piotr and
Kubis, Marek and
Sk{\'o}rzewski, Pawe{\l} and
Wierzchon, Piotr",
editor = "De Clercq, Orph{\'e}e and
Barriere, Valentin and
Barnes, Jeremy and
Klinger, Roman and
Sedoc, Jo{\~a}o and
Tafreshi, Shabnam",
booktitle = "Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, {\&} Social Media Analysis",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.wassa-1.20",
pages = "250--263",
abstract = "This paper presents the POLygraph dataset, a unique resource for fake news detection in Polish. The dataset, created by an interdisciplinary team, is composed of two parts: the {``}fake-or-not{''} dataset with 11,360 pairs of news articles (identified by their URLs) and corresponding labels, and the {``}fake-they-say{''} dataset with 5,082 news articles (identified by their URLs) and tweets commenting on them. Unlike existing datasets, POLygraph encompasses a variety of approaches from source literature, providing a comprehensive resource for fake news detection. The data was collected through manual annotation by expert and non-expert annotators. The project also developed a software tool that uses advanced machine learning techniques to analyze the data and determine content authenticity. The tool and dataset are expected to benefit various entities, from public sector institutions to publishers and fact-checking organizations. Further dataset exploration will foster fake news detection and potentially stimulate the implementation of similar models in other languages. The paper focuses on the creation and composition of the dataset, so it does not include a detailed evaluation of the software tool for content authenticity analysis, which is planned at a later stage of the project.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dzienisiewicz-etal-2024-polygraph">
<titleInfo>
<title>POLygraph: Polish Fake News Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Dzienisiewicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Filip</namePart>
<namePart type="family">Graliński</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Jabłoński</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marek</namePart>
<namePart type="family">Kubis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paweł</namePart>
<namePart type="family">Skórzewski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piotr</namePart>
<namePart type="family">Wierzchon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Orphée</namePart>
<namePart type="family">De Clercq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Barriere</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeremy</namePart>
<namePart type="family">Barnes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Klinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shabnam</namePart>
<namePart type="family">Tafreshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the POLygraph dataset, a unique resource for fake news detection in Polish. The dataset, created by an interdisciplinary team, is composed of two parts: the “fake-or-not” dataset with 11,360 pairs of news articles (identified by their URLs) and corresponding labels, and the “fake-they-say” dataset with 5,082 news articles (identified by their URLs) and tweets commenting on them. Unlike existing datasets, POLygraph encompasses a variety of approaches from source literature, providing a comprehensive resource for fake news detection. The data was collected through manual annotation by expert and non-expert annotators. The project also developed a software tool that uses advanced machine learning techniques to analyze the data and determine content authenticity. The tool and dataset are expected to benefit various entities, from public sector institutions to publishers and fact-checking organizations. Further dataset exploration will foster fake news detection and potentially stimulate the implementation of similar models in other languages. The paper focuses on the creation and composition of the dataset, so it does not include a detailed evaluation of the software tool for content authenticity analysis, which is planned at a later stage of the project.</abstract>
<identifier type="citekey">dzienisiewicz-etal-2024-polygraph</identifier>
<location>
<url>https://aclanthology.org/2024.wassa-1.20</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>250</start>
<end>263</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T POLygraph: Polish Fake News Dataset
%A Dzienisiewicz, Daniel
%A Graliński, Filip
%A Jabłoński, Piotr
%A Kubis, Marek
%A Skórzewski, Paweł
%A Wierzchon, Piotr
%Y De Clercq, Orphée
%Y Barriere, Valentin
%Y Barnes, Jeremy
%Y Klinger, Roman
%Y Sedoc, João
%Y Tafreshi, Shabnam
%S Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F dzienisiewicz-etal-2024-polygraph
%X This paper presents the POLygraph dataset, a unique resource for fake news detection in Polish. The dataset, created by an interdisciplinary team, is composed of two parts: the “fake-or-not” dataset with 11,360 pairs of news articles (identified by their URLs) and corresponding labels, and the “fake-they-say” dataset with 5,082 news articles (identified by their URLs) and tweets commenting on them. Unlike existing datasets, POLygraph encompasses a variety of approaches from source literature, providing a comprehensive resource for fake news detection. The data was collected through manual annotation by expert and non-expert annotators. The project also developed a software tool that uses advanced machine learning techniques to analyze the data and determine content authenticity. The tool and dataset are expected to benefit various entities, from public sector institutions to publishers and fact-checking organizations. Further dataset exploration will foster fake news detection and potentially stimulate the implementation of similar models in other languages. The paper focuses on the creation and composition of the dataset, so it does not include a detailed evaluation of the software tool for content authenticity analysis, which is planned at a later stage of the project.
%U https://aclanthology.org/2024.wassa-1.20
%P 250-263
Markdown (Informal)
[POLygraph: Polish Fake News Dataset](https://aclanthology.org/2024.wassa-1.20) (Dzienisiewicz et al., WASSA-WS 2024)
ACL
- Daniel Dzienisiewicz, Filip Graliński, Piotr Jabłoński, Marek Kubis, Paweł Skórzewski, and Piotr Wierzchon. 2024. POLygraph: Polish Fake News Dataset. In Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis, pages 250–263, Bangkok, Thailand. Association for Computational Linguistics.