@inproceedings{alhindi-etal-2021-arastance,
title = "{A}ra{S}tance: A Multi-Country and Multi-Domain Dataset of {A}rabic Stance Detection for Fact Checking",
author = "Alhindi, Tariq and
Alabdulkarim, Amal and
Alshehri, Ali and
Abdul-Mageed, Muhammad and
Nakov, Preslav",
editor = "Feldman, Anna and
Da San Martino, Giovanni and
Leberknight, Chris and
Nakov, Preslav",
booktitle = "Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.nlp4if-1.9",
doi = "10.18653/v1/2021.nlp4if-1.9",
pages = "57--65",
abstract = "With the continuing spread of misinformation and disinformation online, it is of increasing importance to develop combating mechanisms at scale in the form of automated systems that support multiple languages. One task of interest is claim veracity prediction, which can be addressed using stance detection with respect to relevant documents retrieved online. To this end, we present our new Arabic Stance Detection dataset (AraStance) of 4,063 claim{--}article pairs from a diverse set of sources comprising three fact-checking websites and one news website. AraStance covers false and true claims from multiple domains (e.g., politics, sports, health) and several Arab countries, and it is well-balanced between related and unrelated documents with respect to the claims. We benchmark AraStance, along with two other stance detection datasets, using a number of BERT-based models. Our best model achieves an accuracy of 85{\%} and a macro F1 score of 78{\%}, which leaves room for improvement and reflects the challenging nature of AraStance and the task of stance detection in general.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alhindi-etal-2021-arastance">
<titleInfo>
<title>AraStance: A Multi-Country and Multi-Domain Dataset of Arabic Stance Detection for Fact Checking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tariq</namePart>
<namePart type="family">Alhindi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amal</namePart>
<namePart type="family">Alabdulkarim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Alshehri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Feldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Leberknight</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the continuing spread of misinformation and disinformation online, it is of increasing importance to develop combating mechanisms at scale in the form of automated systems that support multiple languages. One task of interest is claim veracity prediction, which can be addressed using stance detection with respect to relevant documents retrieved online. To this end, we present our new Arabic Stance Detection dataset (AraStance) of 4,063 claim–article pairs from a diverse set of sources comprising three fact-checking websites and one news website. AraStance covers false and true claims from multiple domains (e.g., politics, sports, health) and several Arab countries, and it is well-balanced between related and unrelated documents with respect to the claims. We benchmark AraStance, along with two other stance detection datasets, using a number of BERT-based models. Our best model achieves an accuracy of 85% and a macro F1 score of 78%, which leaves room for improvement and reflects the challenging nature of AraStance and the task of stance detection in general.</abstract>
<identifier type="citekey">alhindi-etal-2021-arastance</identifier>
<identifier type="doi">10.18653/v1/2021.nlp4if-1.9</identifier>
<location>
<url>https://aclanthology.org/2021.nlp4if-1.9</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>57</start>
<end>65</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AraStance: A Multi-Country and Multi-Domain Dataset of Arabic Stance Detection for Fact Checking
%A Alhindi, Tariq
%A Alabdulkarim, Amal
%A Alshehri, Ali
%A Abdul-Mageed, Muhammad
%A Nakov, Preslav
%Y Feldman, Anna
%Y Da San Martino, Giovanni
%Y Leberknight, Chris
%Y Nakov, Preslav
%S Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F alhindi-etal-2021-arastance
%X With the continuing spread of misinformation and disinformation online, it is of increasing importance to develop combating mechanisms at scale in the form of automated systems that support multiple languages. One task of interest is claim veracity prediction, which can be addressed using stance detection with respect to relevant documents retrieved online. To this end, we present our new Arabic Stance Detection dataset (AraStance) of 4,063 claim–article pairs from a diverse set of sources comprising three fact-checking websites and one news website. AraStance covers false and true claims from multiple domains (e.g., politics, sports, health) and several Arab countries, and it is well-balanced between related and unrelated documents with respect to the claims. We benchmark AraStance, along with two other stance detection datasets, using a number of BERT-based models. Our best model achieves an accuracy of 85% and a macro F1 score of 78%, which leaves room for improvement and reflects the challenging nature of AraStance and the task of stance detection in general.
%R 10.18653/v1/2021.nlp4if-1.9
%U https://aclanthology.org/2021.nlp4if-1.9
%U https://doi.org/10.18653/v1/2021.nlp4if-1.9
%P 57-65
Markdown (Informal)
[AraStance: A Multi-Country and Multi-Domain Dataset of Arabic Stance Detection for Fact Checking](https://aclanthology.org/2021.nlp4if-1.9) (Alhindi et al., NLP4IF 2021)
ACL