@inproceedings{fsih-etal-2022-benchmarking,
title = "Benchmarking transfer learning approaches for sentiment analysis of {A}rabic dialect",
author = "Fsih, Emna and
Kchaou, Sameh and
Boujelbane, Rahma and
Hadrich-Belguith, Lamia",
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-1.44",
doi = "10.18653/v1/2022.wanlp-1.44",
pages = "431--435",
abstract = "Arabic has a widely varying collection of dialects. With the explosion of the use of social networks, the volume of written texts has remarkably increased. Most users express themselves using their own dialect. Unfortunately, many of these dialects remain under-studied due to the scarcity of resources. Researchers and industry practitioners are increasingly interested in analyzing users{'} sentiments. In this context, several approaches have been proposed, namely: traditional machine learning, deep learning transfer learning and more recently few-shot learning approaches. In this work, we compare their efficiency as part of the NADI competition to develop a country-level sentiment analysis model. Three models were beneficial for this sub-task: The first based on Sentence Transformer (ST) and achieve 43.23{\%} on DEV set and 42.33{\%} on TEST set, the second based on CAMeLBERT and achieve 47.85{\%} on DEV set and 41.72{\%} on TEST set and the third based on multi-dialect BERT model and achieve 66.72{\%} on DEV set and 39.69{\%} on TEST set.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fsih-etal-2022-benchmarking">
<titleInfo>
<title>Benchmarking transfer learning approaches for sentiment analysis of Arabic dialect</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emna</namePart>
<namePart type="family">Fsih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sameh</namePart>
<namePart type="family">Kchaou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahma</namePart>
<namePart type="family">Boujelbane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lamia</namePart>
<namePart type="family">Hadrich-Belguith</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>Arabic has a widely varying collection of dialects. With the explosion of the use of social networks, the volume of written texts has remarkably increased. Most users express themselves using their own dialect. Unfortunately, many of these dialects remain under-studied due to the scarcity of resources. Researchers and industry practitioners are increasingly interested in analyzing users’ sentiments. In this context, several approaches have been proposed, namely: traditional machine learning, deep learning transfer learning and more recently few-shot learning approaches. In this work, we compare their efficiency as part of the NADI competition to develop a country-level sentiment analysis model. Three models were beneficial for this sub-task: The first based on Sentence Transformer (ST) and achieve 43.23% on DEV set and 42.33% on TEST set, the second based on CAMeLBERT and achieve 47.85% on DEV set and 41.72% on TEST set and the third based on multi-dialect BERT model and achieve 66.72% on DEV set and 39.69% on TEST set.</abstract>
<identifier type="citekey">fsih-etal-2022-benchmarking</identifier>
<identifier type="doi">10.18653/v1/2022.wanlp-1.44</identifier>
<location>
<url>https://aclanthology.org/2022.wanlp-1.44</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>431</start>
<end>435</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmarking transfer learning approaches for sentiment analysis of Arabic dialect
%A Fsih, Emna
%A Kchaou, Sameh
%A Boujelbane, Rahma
%A Hadrich-Belguith, Lamia
%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 fsih-etal-2022-benchmarking
%X Arabic has a widely varying collection of dialects. With the explosion of the use of social networks, the volume of written texts has remarkably increased. Most users express themselves using their own dialect. Unfortunately, many of these dialects remain under-studied due to the scarcity of resources. Researchers and industry practitioners are increasingly interested in analyzing users’ sentiments. In this context, several approaches have been proposed, namely: traditional machine learning, deep learning transfer learning and more recently few-shot learning approaches. In this work, we compare their efficiency as part of the NADI competition to develop a country-level sentiment analysis model. Three models were beneficial for this sub-task: The first based on Sentence Transformer (ST) and achieve 43.23% on DEV set and 42.33% on TEST set, the second based on CAMeLBERT and achieve 47.85% on DEV set and 41.72% on TEST set and the third based on multi-dialect BERT model and achieve 66.72% on DEV set and 39.69% on TEST set.
%R 10.18653/v1/2022.wanlp-1.44
%U https://aclanthology.org/2022.wanlp-1.44
%U https://doi.org/10.18653/v1/2022.wanlp-1.44
%P 431-435
Markdown (Informal)
[Benchmarking transfer learning approaches for sentiment analysis of Arabic dialect](https://aclanthology.org/2022.wanlp-1.44) (Fsih et al., WANLP 2022)
ACL