@inproceedings{hacohen-kerner-etal-2022-jct-semeval,
title = "{JCT} at {S}em{E}val-2022 Task 6-A: Sarcasm Detection in Tweets Written in {E}nglish and {A}rabic using Preprocessing Methods and Word N-grams",
author = "HaCohen-Kerner, Yaakov and
Fchima, Matan and
Meyrowitsch, Ilan",
editor = "Emerson, Guy and
Schluter, Natalie and
Stanovsky, Gabriel and
Kumar, Ritesh and
Palmer, Alexis and
Schneider, Nathan and
Singh, Siddharth and
Ratan, Shyam",
booktitle = "Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.semeval-1.145",
doi = "10.18653/v1/2022.semeval-1.145",
pages = "1031--1038",
abstract = "In this paper, we describe our submissions to SemEval-2022 contest. We tackled subtask 6-A - {``}iSarcasmEval: Intended Sarcasm Detection In English and Arabic {--} Binary Classification{''}. We developed different models for two languages: English and Arabic. We applied 4 supervised machine learning methods, 6 preprocessing methods for English and 3 for Arabic, and 3 oversampling methods. Our best submitted model for the English test dataset was a SVC model that balanced the dataset using SMOTE and removed stop words. For the Arabic test dataset our best submitted model was a SVC model that preprocessed removed longation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hacohen-kerner-etal-2022-jct-semeval">
<titleInfo>
<title>JCT at SemEval-2022 Task 6-A: Sarcasm Detection in Tweets Written in English and Arabic using Preprocessing Methods and Word N-grams</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaakov</namePart>
<namePart type="family">HaCohen-Kerner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matan</namePart>
<namePart type="family">Fchima</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilan</namePart>
<namePart type="family">Meyrowitsch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Emerson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Stanovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shyam</namePart>
<namePart type="family">Ratan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we describe our submissions to SemEval-2022 contest. We tackled subtask 6-A - “iSarcasmEval: Intended Sarcasm Detection In English and Arabic – Binary Classification”. We developed different models for two languages: English and Arabic. We applied 4 supervised machine learning methods, 6 preprocessing methods for English and 3 for Arabic, and 3 oversampling methods. Our best submitted model for the English test dataset was a SVC model that balanced the dataset using SMOTE and removed stop words. For the Arabic test dataset our best submitted model was a SVC model that preprocessed removed longation.</abstract>
<identifier type="citekey">hacohen-kerner-etal-2022-jct-semeval</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.145</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.145</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1031</start>
<end>1038</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T JCT at SemEval-2022 Task 6-A: Sarcasm Detection in Tweets Written in English and Arabic using Preprocessing Methods and Word N-grams
%A HaCohen-Kerner, Yaakov
%A Fchima, Matan
%A Meyrowitsch, Ilan
%Y Emerson, Guy
%Y Schluter, Natalie
%Y Stanovsky, Gabriel
%Y Kumar, Ritesh
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y Singh, Siddharth
%Y Ratan, Shyam
%S Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F hacohen-kerner-etal-2022-jct-semeval
%X In this paper, we describe our submissions to SemEval-2022 contest. We tackled subtask 6-A - “iSarcasmEval: Intended Sarcasm Detection In English and Arabic – Binary Classification”. We developed different models for two languages: English and Arabic. We applied 4 supervised machine learning methods, 6 preprocessing methods for English and 3 for Arabic, and 3 oversampling methods. Our best submitted model for the English test dataset was a SVC model that balanced the dataset using SMOTE and removed stop words. For the Arabic test dataset our best submitted model was a SVC model that preprocessed removed longation.
%R 10.18653/v1/2022.semeval-1.145
%U https://aclanthology.org/2022.semeval-1.145
%U https://doi.org/10.18653/v1/2022.semeval-1.145
%P 1031-1038
Markdown (Informal)
[JCT at SemEval-2022 Task 6-A: Sarcasm Detection in Tweets Written in English and Arabic using Preprocessing Methods and Word N-grams](https://aclanthology.org/2022.semeval-1.145) (HaCohen-Kerner et al., SemEval 2022)
ACL