@inproceedings{el-ballouli-etal-2017-cat,
title = "{CAT}: Credibility Analysis of {A}rabic Content on {T}witter",
author = "El Ballouli, Rim and
El-Hajj, Wassim and
Ghandour, Ahmad and
Elbassuoni, Shady and
Hajj, Hazem and
Shaban, Khaled",
editor = "Habash, Nizar and
Diab, Mona and
Darwish, Kareem and
El-Hajj, Wassim and
Al-Khalifa, Hend and
Bouamor, Houda and
Tomeh, Nadi and
El-Haj, Mahmoud and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Third {A}rabic Natural Language Processing Workshop",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-1308",
doi = "10.18653/v1/W17-1308",
pages = "62--71",
abstract = "Data generated on Twitter has become a rich source for various data mining tasks. Those data analysis tasks that are dependent on the tweet semantics, such as sentiment analysis, emotion mining, and rumor detection among others, suffer considerably if the tweet is not credible, not real, or spam. In this paper, we perform an extensive analysis on credibility of Arabic content on Twitter. We also build a classification model (CAT) to automatically predict the credibility of a given Arabic tweet. Of particular originality is the inclusion of features extracted directly or indirectly from the author{'}s profile and timeline. To train and test CAT, we annotated for credibility a data set of 9,000 Arabic tweets that are topic independent. CAT achieved consistent improvements in predicting the credibility of the tweets when compared to several baselines and when compared to the state-of-the-art approach with an improvement of 21{\%} in weighted average F-measure. We also conducted experiments to highlight the importance of the user-based features as opposed to the content-based features. We conclude our work with a feature reduction experiment that highlights the best indicative features of credibility.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="el-ballouli-etal-2017-cat">
<titleInfo>
<title>CAT: Credibility Analysis of Arabic Content on Twitter</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rim</namePart>
<namePart type="family">El Ballouli</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">Ahmad</namePart>
<namePart type="family">Ghandour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shady</namePart>
<namePart type="family">Elbassuoni</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>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Arabic Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Diab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wassim</namePart>
<namePart type="family">El-Hajj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Data generated on Twitter has become a rich source for various data mining tasks. Those data analysis tasks that are dependent on the tweet semantics, such as sentiment analysis, emotion mining, and rumor detection among others, suffer considerably if the tweet is not credible, not real, or spam. In this paper, we perform an extensive analysis on credibility of Arabic content on Twitter. We also build a classification model (CAT) to automatically predict the credibility of a given Arabic tweet. Of particular originality is the inclusion of features extracted directly or indirectly from the author’s profile and timeline. To train and test CAT, we annotated for credibility a data set of 9,000 Arabic tweets that are topic independent. CAT achieved consistent improvements in predicting the credibility of the tweets when compared to several baselines and when compared to the state-of-the-art approach with an improvement of 21% in weighted average F-measure. We also conducted experiments to highlight the importance of the user-based features as opposed to the content-based features. We conclude our work with a feature reduction experiment that highlights the best indicative features of credibility.</abstract>
<identifier type="citekey">el-ballouli-etal-2017-cat</identifier>
<identifier type="doi">10.18653/v1/W17-1308</identifier>
<location>
<url>https://aclanthology.org/W17-1308</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>62</start>
<end>71</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CAT: Credibility Analysis of Arabic Content on Twitter
%A El Ballouli, Rim
%A El-Hajj, Wassim
%A Ghandour, Ahmad
%A Elbassuoni, Shady
%A Hajj, Hazem
%A Shaban, Khaled
%Y Habash, Nizar
%Y Diab, Mona
%Y Darwish, Kareem
%Y El-Hajj, Wassim
%Y Al-Khalifa, Hend
%Y Bouamor, Houda
%Y Tomeh, Nadi
%Y El-Haj, Mahmoud
%Y Zaghouani, Wajdi
%S Proceedings of the Third Arabic Natural Language Processing Workshop
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F el-ballouli-etal-2017-cat
%X Data generated on Twitter has become a rich source for various data mining tasks. Those data analysis tasks that are dependent on the tweet semantics, such as sentiment analysis, emotion mining, and rumor detection among others, suffer considerably if the tweet is not credible, not real, or spam. In this paper, we perform an extensive analysis on credibility of Arabic content on Twitter. We also build a classification model (CAT) to automatically predict the credibility of a given Arabic tweet. Of particular originality is the inclusion of features extracted directly or indirectly from the author’s profile and timeline. To train and test CAT, we annotated for credibility a data set of 9,000 Arabic tweets that are topic independent. CAT achieved consistent improvements in predicting the credibility of the tweets when compared to several baselines and when compared to the state-of-the-art approach with an improvement of 21% in weighted average F-measure. We also conducted experiments to highlight the importance of the user-based features as opposed to the content-based features. We conclude our work with a feature reduction experiment that highlights the best indicative features of credibility.
%R 10.18653/v1/W17-1308
%U https://aclanthology.org/W17-1308
%U https://doi.org/10.18653/v1/W17-1308
%P 62-71
Markdown (Informal)
[CAT: Credibility Analysis of Arabic Content on Twitter](https://aclanthology.org/W17-1308) (El Ballouli et al., WANLP 2017)
ACL
- Rim El Ballouli, Wassim El-Hajj, Ahmad Ghandour, Shady Elbassuoni, Hazem Hajj, and Khaled Shaban. 2017. CAT: Credibility Analysis of Arabic Content on Twitter. In Proceedings of the Third Arabic Natural Language Processing Workshop, pages 62–71, Valencia, Spain. Association for Computational Linguistics.