@inproceedings{nakamura-etal-2020-fakeddit,
title = "{F}akeddit: A New Multimodal Benchmark Dataset for Fine-grained Fake News Detection",
author = "Nakamura, Kai and
Levy, Sharon and
Wang, William Yang",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.755",
pages = "6149--6157",
abstract = "Fake news has altered society in negative ways in politics and culture. It has adversely affected both online social network systems as well as offline communities and conversations. Using automatic machine learning classification models is an efficient way to combat the widespread dissemination of fake news. However, a lack of effective, comprehensive datasets has been a problem for fake news research and detection model development. Prior fake news datasets do not provide multimodal text and image data, metadata, comment data, and fine-grained fake news categorization at the scale and breadth of our dataset. We present Fakeddit, a novel multimodal dataset consisting of over 1 million samples from multiple categories of fake news. After being processed through several stages of review, the samples are labeled according to 2-way, 3-way, and 6-way classification categories through distant supervision. We construct hybrid text+image models and perform extensive experiments for multiple variations of classification, demonstrating the importance of the novel aspect of multimodality and fine-grained classification unique to Fakeddit.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nakamura-etal-2020-fakeddit">
<titleInfo>
<title>Fakeddit: A New Multimodal Benchmark Dataset for Fine-grained Fake News Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Nakamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharon</namePart>
<namePart type="family">Levy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="given">Yang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Fake news has altered society in negative ways in politics and culture. It has adversely affected both online social network systems as well as offline communities and conversations. Using automatic machine learning classification models is an efficient way to combat the widespread dissemination of fake news. However, a lack of effective, comprehensive datasets has been a problem for fake news research and detection model development. Prior fake news datasets do not provide multimodal text and image data, metadata, comment data, and fine-grained fake news categorization at the scale and breadth of our dataset. We present Fakeddit, a novel multimodal dataset consisting of over 1 million samples from multiple categories of fake news. After being processed through several stages of review, the samples are labeled according to 2-way, 3-way, and 6-way classification categories through distant supervision. We construct hybrid text+image models and perform extensive experiments for multiple variations of classification, demonstrating the importance of the novel aspect of multimodality and fine-grained classification unique to Fakeddit.</abstract>
<identifier type="citekey">nakamura-etal-2020-fakeddit</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.755</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6149</start>
<end>6157</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fakeddit: A New Multimodal Benchmark Dataset for Fine-grained Fake News Detection
%A Nakamura, Kai
%A Levy, Sharon
%A Wang, William Yang
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F nakamura-etal-2020-fakeddit
%X Fake news has altered society in negative ways in politics and culture. It has adversely affected both online social network systems as well as offline communities and conversations. Using automatic machine learning classification models is an efficient way to combat the widespread dissemination of fake news. However, a lack of effective, comprehensive datasets has been a problem for fake news research and detection model development. Prior fake news datasets do not provide multimodal text and image data, metadata, comment data, and fine-grained fake news categorization at the scale and breadth of our dataset. We present Fakeddit, a novel multimodal dataset consisting of over 1 million samples from multiple categories of fake news. After being processed through several stages of review, the samples are labeled according to 2-way, 3-way, and 6-way classification categories through distant supervision. We construct hybrid text+image models and perform extensive experiments for multiple variations of classification, demonstrating the importance of the novel aspect of multimodality and fine-grained classification unique to Fakeddit.
%U https://aclanthology.org/2020.lrec-1.755
%P 6149-6157
Markdown (Informal)
[Fakeddit: A New Multimodal Benchmark Dataset for Fine-grained Fake News Detection](https://aclanthology.org/2020.lrec-1.755) (Nakamura et al., LREC 2020)
ACL