@inproceedings{bahaaulddin-etal-2023-aradetector,
title = "{A}ra{D}etector at {A}r{AIE}val Shared Task: An Ensemble of {A}rabic-specific pre-trained {BERT} and {GPT}-4 for {A}rabic Disinformation Detection",
author = "Bahaaulddin, Ahmed and
Sabeeh, Vian and
Belhaj, Hanan and
Sibaee, Serry and
Ahmad, Samar and
Khurfan, Ibrahim and
Alharbi, Abdullah",
editor = "Sawaf, Hassan and
El-Beltagy, Samhaa and
Zaghouani, Wajdi and
Magdy, Walid and
Abdelali, Ahmed and
Tomeh, Nadi and
Abu Farha, Ibrahim and
Habash, Nizar and
Khalifa, Salam and
Keleg, Amr and
Haddad, Hatem and
Zitouni, Imed and
Mrini, Khalil and
Almatham, Rawan",
booktitle = "Proceedings of ArabicNLP 2023",
month = dec,
year = "2023",
address = "Singapore (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.arabicnlp-1.51",
doi = "10.18653/v1/2023.arabicnlp-1.51",
pages = "530--535",
abstract = "The rapid proliferation of disinformation through social media has become one of the most dangerous means to deceive and influence people{'}s thoughts, viewpoints, or behaviors due to social media{'}s facilities, such as rapid access, lower cost, and ease of use. Disinformation can spread through social media in different ways, such as fake news stories, doctored images or videos, deceptive data, and even conspiracy theories, thus making detecting disinformation challenging. This paper is a part of participation in the ArAIEval competition that relates to disinformation detection. This work evaluated four models: MARBERT, the proposed ensemble model, and two tests over GPT-4 (zero-shot and Few-shot). GPT-4 achieved micro-F1 79.01{\%} while the ensemble method obtained 76.83{\%}. Despite no improvement in the micro-F1 score on the dev dataset using the ensemble approach, we still used it for the test dataset predictions. We believed that merging different classifiers might enhance the system{'}s prediction accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bahaaulddin-etal-2023-aradetector">
<titleInfo>
<title>AraDetector at ArAIEval Shared Task: An Ensemble of Arabic-specific pre-trained BERT and GPT-4 for Arabic Disinformation Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Bahaaulddin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vian</namePart>
<namePart type="family">Sabeeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanan</namePart>
<namePart type="family">Belhaj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serry</namePart>
<namePart type="family">Sibaee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Ahmad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Khurfan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdullah</namePart>
<namePart type="family">Alharbi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of ArabicNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Sawaf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</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>
<name type="personal">
<namePart type="given">Walid</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</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">Ibrahim</namePart>
<namePart type="family">Abu Farha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amr</namePart>
<namePart type="family">Keleg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hatem</namePart>
<namePart type="family">Haddad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Mrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rawan</namePart>
<namePart type="family">Almatham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The rapid proliferation of disinformation through social media has become one of the most dangerous means to deceive and influence people’s thoughts, viewpoints, or behaviors due to social media’s facilities, such as rapid access, lower cost, and ease of use. Disinformation can spread through social media in different ways, such as fake news stories, doctored images or videos, deceptive data, and even conspiracy theories, thus making detecting disinformation challenging. This paper is a part of participation in the ArAIEval competition that relates to disinformation detection. This work evaluated four models: MARBERT, the proposed ensemble model, and two tests over GPT-4 (zero-shot and Few-shot). GPT-4 achieved micro-F1 79.01% while the ensemble method obtained 76.83%. Despite no improvement in the micro-F1 score on the dev dataset using the ensemble approach, we still used it for the test dataset predictions. We believed that merging different classifiers might enhance the system’s prediction accuracy.</abstract>
<identifier type="citekey">bahaaulddin-etal-2023-aradetector</identifier>
<identifier type="doi">10.18653/v1/2023.arabicnlp-1.51</identifier>
<location>
<url>https://aclanthology.org/2023.arabicnlp-1.51</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>530</start>
<end>535</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AraDetector at ArAIEval Shared Task: An Ensemble of Arabic-specific pre-trained BERT and GPT-4 for Arabic Disinformation Detection
%A Bahaaulddin, Ahmed
%A Sabeeh, Vian
%A Belhaj, Hanan
%A Sibaee, Serry
%A Ahmad, Samar
%A Khurfan, Ibrahim
%A Alharbi, Abdullah
%Y Sawaf, Hassan
%Y El-Beltagy, Samhaa
%Y Zaghouani, Wajdi
%Y Magdy, Walid
%Y Abdelali, Ahmed
%Y Tomeh, Nadi
%Y Abu Farha, Ibrahim
%Y Habash, Nizar
%Y Khalifa, Salam
%Y Keleg, Amr
%Y Haddad, Hatem
%Y Zitouni, Imed
%Y Mrini, Khalil
%Y Almatham, Rawan
%S Proceedings of ArabicNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore (Hybrid)
%F bahaaulddin-etal-2023-aradetector
%X The rapid proliferation of disinformation through social media has become one of the most dangerous means to deceive and influence people’s thoughts, viewpoints, or behaviors due to social media’s facilities, such as rapid access, lower cost, and ease of use. Disinformation can spread through social media in different ways, such as fake news stories, doctored images or videos, deceptive data, and even conspiracy theories, thus making detecting disinformation challenging. This paper is a part of participation in the ArAIEval competition that relates to disinformation detection. This work evaluated four models: MARBERT, the proposed ensemble model, and two tests over GPT-4 (zero-shot and Few-shot). GPT-4 achieved micro-F1 79.01% while the ensemble method obtained 76.83%. Despite no improvement in the micro-F1 score on the dev dataset using the ensemble approach, we still used it for the test dataset predictions. We believed that merging different classifiers might enhance the system’s prediction accuracy.
%R 10.18653/v1/2023.arabicnlp-1.51
%U https://aclanthology.org/2023.arabicnlp-1.51
%U https://doi.org/10.18653/v1/2023.arabicnlp-1.51
%P 530-535
Markdown (Informal)
[AraDetector at ArAIEval Shared Task: An Ensemble of Arabic-specific pre-trained BERT and GPT-4 for Arabic Disinformation Detection](https://aclanthology.org/2023.arabicnlp-1.51) (Bahaaulddin et al., ArabicNLP-WS 2023)
ACL