@inproceedings{zaatari-etal-2016-arabic,
title = "{A}rabic Corpora for Credibility Analysis",
author = "Zaatari, Ayman Al and
Ballouli, Rim El and
ELbassouni, Shady and
El-Hajj, Wassim and
Hajj, Hazem and
Shaban, Khaled and
Habash, Nizar and
Yahya, Emad",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1696/",
pages = "4396--4401",
abstract = "A significant portion of data generated on blogging and microblogging websites is non-credible as shown in many recent studies. To filter out such non-credible information, machine learning can be deployed to build automatic credibility classifiers. However, as in the case with most supervised machine learning approaches, a sufficiently large and accurate training data must be available. In this paper, we focus on building a public Arabic corpus of blogs and microblogs that can be used for credibility classification. We focus on Arabic due to the recent popularity of blogs and microblogs in the Arab World and due to the lack of any such public corpora in Arabic. We discuss our data acquisition approach and annotation process, provide rigid analysis on the annotated data and finally report some results on the effectiveness of our data for credibility classification."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zaatari-etal-2016-arabic">
<titleInfo>
<title>Arabic Corpora for Credibility Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ayman</namePart>
<namePart type="given">Al</namePart>
<namePart type="family">Zaatari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rim</namePart>
<namePart type="given">El</namePart>
<namePart type="family">Ballouli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shady</namePart>
<namePart type="family">ELbassouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wassim</namePart>
<namePart type="family">El-Hajj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hazem</namePart>
<namePart type="family">Hajj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khaled</namePart>
<namePart type="family">Shaban</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emad</namePart>
<namePart type="family">Yahya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A significant portion of data generated on blogging and microblogging websites is non-credible as shown in many recent studies. To filter out such non-credible information, machine learning can be deployed to build automatic credibility classifiers. However, as in the case with most supervised machine learning approaches, a sufficiently large and accurate training data must be available. In this paper, we focus on building a public Arabic corpus of blogs and microblogs that can be used for credibility classification. We focus on Arabic due to the recent popularity of blogs and microblogs in the Arab World and due to the lack of any such public corpora in Arabic. We discuss our data acquisition approach and annotation process, provide rigid analysis on the annotated data and finally report some results on the effectiveness of our data for credibility classification.</abstract>
<identifier type="citekey">zaatari-etal-2016-arabic</identifier>
<location>
<url>https://aclanthology.org/L16-1696/</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4396</start>
<end>4401</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Arabic Corpora for Credibility Analysis
%A Zaatari, Ayman Al
%A Ballouli, Rim El
%A ELbassouni, Shady
%A El-Hajj, Wassim
%A Hajj, Hazem
%A Shaban, Khaled
%A Habash, Nizar
%A Yahya, Emad
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F zaatari-etal-2016-arabic
%X A significant portion of data generated on blogging and microblogging websites is non-credible as shown in many recent studies. To filter out such non-credible information, machine learning can be deployed to build automatic credibility classifiers. However, as in the case with most supervised machine learning approaches, a sufficiently large and accurate training data must be available. In this paper, we focus on building a public Arabic corpus of blogs and microblogs that can be used for credibility classification. We focus on Arabic due to the recent popularity of blogs and microblogs in the Arab World and due to the lack of any such public corpora in Arabic. We discuss our data acquisition approach and annotation process, provide rigid analysis on the annotated data and finally report some results on the effectiveness of our data for credibility classification.
%U https://aclanthology.org/L16-1696/
%P 4396-4401
Markdown (Informal)
[Arabic Corpora for Credibility Analysis](https://aclanthology.org/L16-1696/) (Zaatari et al., LREC 2016)
ACL
- Ayman Al Zaatari, Rim El Ballouli, Shady ELbassouni, Wassim El-Hajj, Hazem Hajj, Khaled Shaban, Nizar Habash, and Emad Yahya. 2016. Arabic Corpora for Credibility Analysis. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 4396–4401, Portorož, Slovenia. European Language Resources Association (ELRA).