@inproceedings{mersinias-etal-2020-clfd,
title = "{CLFD}: A Novel Vectorization Technique and Its Application in Fake News Detection",
author = "Mersinias, Michail and
Afantenos, Stergos and
Chalkiadakis, Georgios",
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-1.427/",
pages = "3475--3483",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "In recent years, fake news detection has been an emerging research area. In this paper, we put forward a novel statistical approach for the generation of feature vectors to describe a document. Our so-called class label frequency distance (clfd), is shown experimentally to provide an effective way for boosting the performance of machine learning methods. Specifically, our experiments, carried out in the fake news detection domain, verify that efficient traditional machine learning methods that use our vectorization approach, consistently outperform deep learning methods that use word embeddings for small and medium sized datasets, while the results are comparable for large datasets. In addition, we demonstrate that a novel hybrid method that utilizes both a clfd-boosted logistic regression classifier and a deep learning one, clearly outperforms deep learning methods even in large datasets."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mersinias-etal-2020-clfd">
<titleInfo>
<title>CLFD: A Novel Vectorization Technique and Its Application in Fake News Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michail</namePart>
<namePart type="family">Mersinias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stergos</namePart>
<namePart type="family">Afantenos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georgios</namePart>
<namePart type="family">Chalkiadakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">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>In recent years, fake news detection has been an emerging research area. In this paper, we put forward a novel statistical approach for the generation of feature vectors to describe a document. Our so-called class label frequency distance (clfd), is shown experimentally to provide an effective way for boosting the performance of machine learning methods. Specifically, our experiments, carried out in the fake news detection domain, verify that efficient traditional machine learning methods that use our vectorization approach, consistently outperform deep learning methods that use word embeddings for small and medium sized datasets, while the results are comparable for large datasets. In addition, we demonstrate that a novel hybrid method that utilizes both a clfd-boosted logistic regression classifier and a deep learning one, clearly outperforms deep learning methods even in large datasets.</abstract>
<identifier type="citekey">mersinias-etal-2020-clfd</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.427/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>3475</start>
<end>3483</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CLFD: A Novel Vectorization Technique and Its Application in Fake News Detection
%A Mersinias, Michail
%A Afantenos, Stergos
%A Chalkiadakis, Georgios
%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 eng
%F mersinias-etal-2020-clfd
%X In recent years, fake news detection has been an emerging research area. In this paper, we put forward a novel statistical approach for the generation of feature vectors to describe a document. Our so-called class label frequency distance (clfd), is shown experimentally to provide an effective way for boosting the performance of machine learning methods. Specifically, our experiments, carried out in the fake news detection domain, verify that efficient traditional machine learning methods that use our vectorization approach, consistently outperform deep learning methods that use word embeddings for small and medium sized datasets, while the results are comparable for large datasets. In addition, we demonstrate that a novel hybrid method that utilizes both a clfd-boosted logistic regression classifier and a deep learning one, clearly outperforms deep learning methods even in large datasets.
%U https://aclanthology.org/2020.lrec-1.427/
%P 3475-3483
Markdown (Informal)
[CLFD: A Novel Vectorization Technique and Its Application in Fake News Detection](https://aclanthology.org/2020.lrec-1.427/) (Mersinias et al., LREC 2020)
ACL