@inproceedings{abu-farha-magdy-2020-arabic,
title = "From {A}rabic Sentiment Analysis to Sarcasm Detection: The {A}r{S}arcasm Dataset",
author = "Abu Farha, Ibrahim and
Magdy, Walid",
editor = "Al-Khalifa, Hend and
Magdy, Walid and
Darwish, Kareem and
Elsayed, Tamer and
Mubarak, Hamdy",
booktitle = "Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resource Association",
url = "https://aclanthology.org/2020.osact-1.5/",
pages = "32--39",
language = "eng",
ISBN = "979-10-95546-51-1",
abstract = "Sarcasm is one of the main challenges for sentiment analysis systems. Its complexity comes from the expression of opinion using implicit indirect phrasing. In this paper, we present ArSarcasm, an Arabic sarcasm detection dataset, which was created through the reannotation of available Arabic sentiment analysis datasets. The dataset contains 10,547 tweets, 16{\%} of which are sarcastic. In addition to sarcasm the data was annotated for sentiment and dialects. Our analysis shows the highly subjective nature of these tasks, which is demonstrated by the shift in sentiment labels based on annotators' biases. Experiments show the degradation of state-of-the-art sentiment analysers when faced with sarcastic content. Finally, we train a deep learning model for sarcasm detection using BiLSTM. The model achieves an F1 score of 0.46, which shows the challenging nature of the task, and should act as a basic baseline for future research on our dataset."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abu-farha-magdy-2020-arabic">
<titleInfo>
<title>From Arabic Sentiment Analysis to Sarcasm Detection: The ArSarcasm Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Abu Farha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walid</namePart>
<namePart type="family">Magdy</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 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection</title>
</titleInfo>
<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">Walid</namePart>
<namePart type="family">Magdy</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">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamdy</namePart>
<namePart type="family">Mubarak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resource Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-51-1</identifier>
</relatedItem>
<abstract>Sarcasm is one of the main challenges for sentiment analysis systems. Its complexity comes from the expression of opinion using implicit indirect phrasing. In this paper, we present ArSarcasm, an Arabic sarcasm detection dataset, which was created through the reannotation of available Arabic sentiment analysis datasets. The dataset contains 10,547 tweets, 16% of which are sarcastic. In addition to sarcasm the data was annotated for sentiment and dialects. Our analysis shows the highly subjective nature of these tasks, which is demonstrated by the shift in sentiment labels based on annotators’ biases. Experiments show the degradation of state-of-the-art sentiment analysers when faced with sarcastic content. Finally, we train a deep learning model for sarcasm detection using BiLSTM. The model achieves an F1 score of 0.46, which shows the challenging nature of the task, and should act as a basic baseline for future research on our dataset.</abstract>
<identifier type="citekey">abu-farha-magdy-2020-arabic</identifier>
<location>
<url>https://aclanthology.org/2020.osact-1.5/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>32</start>
<end>39</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Arabic Sentiment Analysis to Sarcasm Detection: The ArSarcasm Dataset
%A Abu Farha, Ibrahim
%A Magdy, Walid
%Y Al-Khalifa, Hend
%Y Magdy, Walid
%Y Darwish, Kareem
%Y Elsayed, Tamer
%Y Mubarak, Hamdy
%S Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection
%D 2020
%8 May
%I European Language Resource Association
%C Marseille, France
%@ 979-10-95546-51-1
%G eng
%F abu-farha-magdy-2020-arabic
%X Sarcasm is one of the main challenges for sentiment analysis systems. Its complexity comes from the expression of opinion using implicit indirect phrasing. In this paper, we present ArSarcasm, an Arabic sarcasm detection dataset, which was created through the reannotation of available Arabic sentiment analysis datasets. The dataset contains 10,547 tweets, 16% of which are sarcastic. In addition to sarcasm the data was annotated for sentiment and dialects. Our analysis shows the highly subjective nature of these tasks, which is demonstrated by the shift in sentiment labels based on annotators’ biases. Experiments show the degradation of state-of-the-art sentiment analysers when faced with sarcastic content. Finally, we train a deep learning model for sarcasm detection using BiLSTM. The model achieves an F1 score of 0.46, which shows the challenging nature of the task, and should act as a basic baseline for future research on our dataset.
%U https://aclanthology.org/2020.osact-1.5/
%P 32-39
Markdown (Informal)
[From Arabic Sentiment Analysis to Sarcasm Detection: The ArSarcasm Dataset](https://aclanthology.org/2020.osact-1.5/) (Abu Farha & Magdy, OSACT 2020)
ACL