@inproceedings{husain-etal-2022-weak,
title = "A Weak Supervised Transfer Learning Approach for Sentiment Analysis to the {K}uwaiti Dialect",
author = "Husain, Fatemah and
Al-Ostad, Hana and
Omar, Halima",
editor = "Bouamor, Houda and
Al-Khalifa, Hend and
Darwish, Kareem and
Rambow, Owen and
Bougares, Fethi and
Abdelali, Ahmed and
Tomeh, Nadi and
Khalifa, Salam and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.wanlp-1.15",
doi = "10.18653/v1/2022.wanlp-1.15",
pages = "161--173",
abstract = "Developing a system for sentiment analysis is very challenging for the Arabic language due to the limitations in the available Arabic datasets. Many Arabic dialects are still not studied by researchers in Arabic sentiment analysis due to the complexity of annotators{'} recruitment process during dataset creation. This paper covers the research gap in sentiment analysis for the Kuwaiti dialect by proposing a weak supervised approach to develop a large labeled dataset. Our dataset consists of over 16.6k tweets with 7,905 negatives, 7,902 positives, and 860 neutrals that spans several themes and time frames to remove any bias that might affect its content. The annotation agreement between our proposed system{'}s labels and human-annotated labels reports 93{\%} for the pairwise percent agreement and 0.87 for Cohen{'}s kappa coefficient. Furthermore, we evaluate our dataset using multiple traditional machine learning classifiers and advanced deep learning language models to test its performance. The results report 89{\%} accuracy when applied to the testing dataset using the ARBERT model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="husain-etal-2022-weak">
<titleInfo>
<title>A Weak Supervised Transfer Learning Approach for Sentiment Analysis to the Kuwaiti Dialect</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fatemah</namePart>
<namePart type="family">Husain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hana</namePart>
<namePart type="family">Al-Ostad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Halima</namePart>
<namePart type="family">Omar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)</title>
</titleInfo>
<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">Hend</namePart>
<namePart type="family">Al-Khalifa</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">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</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">Salam</namePart>
<namePart type="family">Khalifa</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">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Developing a system for sentiment analysis is very challenging for the Arabic language due to the limitations in the available Arabic datasets. Many Arabic dialects are still not studied by researchers in Arabic sentiment analysis due to the complexity of annotators’ recruitment process during dataset creation. This paper covers the research gap in sentiment analysis for the Kuwaiti dialect by proposing a weak supervised approach to develop a large labeled dataset. Our dataset consists of over 16.6k tweets with 7,905 negatives, 7,902 positives, and 860 neutrals that spans several themes and time frames to remove any bias that might affect its content. The annotation agreement between our proposed system’s labels and human-annotated labels reports 93% for the pairwise percent agreement and 0.87 for Cohen’s kappa coefficient. Furthermore, we evaluate our dataset using multiple traditional machine learning classifiers and advanced deep learning language models to test its performance. The results report 89% accuracy when applied to the testing dataset using the ARBERT model.</abstract>
<identifier type="citekey">husain-etal-2022-weak</identifier>
<identifier type="doi">10.18653/v1/2022.wanlp-1.15</identifier>
<location>
<url>https://aclanthology.org/2022.wanlp-1.15</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>161</start>
<end>173</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Weak Supervised Transfer Learning Approach for Sentiment Analysis to the Kuwaiti Dialect
%A Husain, Fatemah
%A Al-Ostad, Hana
%A Omar, Halima
%Y Bouamor, Houda
%Y Al-Khalifa, Hend
%Y Darwish, Kareem
%Y Rambow, Owen
%Y Bougares, Fethi
%Y Abdelali, Ahmed
%Y Tomeh, Nadi
%Y Khalifa, Salam
%Y Zaghouani, Wajdi
%S Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F husain-etal-2022-weak
%X Developing a system for sentiment analysis is very challenging for the Arabic language due to the limitations in the available Arabic datasets. Many Arabic dialects are still not studied by researchers in Arabic sentiment analysis due to the complexity of annotators’ recruitment process during dataset creation. This paper covers the research gap in sentiment analysis for the Kuwaiti dialect by proposing a weak supervised approach to develop a large labeled dataset. Our dataset consists of over 16.6k tweets with 7,905 negatives, 7,902 positives, and 860 neutrals that spans several themes and time frames to remove any bias that might affect its content. The annotation agreement between our proposed system’s labels and human-annotated labels reports 93% for the pairwise percent agreement and 0.87 for Cohen’s kappa coefficient. Furthermore, we evaluate our dataset using multiple traditional machine learning classifiers and advanced deep learning language models to test its performance. The results report 89% accuracy when applied to the testing dataset using the ARBERT model.
%R 10.18653/v1/2022.wanlp-1.15
%U https://aclanthology.org/2022.wanlp-1.15
%U https://doi.org/10.18653/v1/2022.wanlp-1.15
%P 161-173
Markdown (Informal)
[A Weak Supervised Transfer Learning Approach for Sentiment Analysis to the Kuwaiti Dialect](https://aclanthology.org/2022.wanlp-1.15) (Husain et al., WANLP 2022)
ACL