@inproceedings{aldihan-etal-2022-pilot,
title = "A Pilot Study on the Collection and Computational Analysis of Linguistic Differences Amongst Men and Women in a Kuwaiti {A}rabic {W}hats{A}pp Dataset",
author = "Aldihan, Hesah and
Gaizauskas, Robert and
Fitzmaurice, Susan",
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-1.35",
doi = "10.18653/v1/2022.wanlp-1.35",
pages = "372--380",
abstract = "This study focuses on the collection and computational analysis of Kuwaiti Arabic (KA), which is considered a low resource dialect, to test different sociolinguistic hypotheses related to gendered language use. In this paper, we describe the collection and analysis of a corpus of WhatsApp Group chats with mixed gender Kuwaiti participants. This corpus, which we are making publicly available, is the first corpus of KA conversational data. We analyse different interactional and linguistic features to get insights about features that may be indicative of gender to inform the development of a gender classification system for KA in an upcoming study. Statistical analysis of our data shows that there is insufficient evidence to claim that there are significant differences amongst men and women with respect to number of turns, length of turns and number of emojis. However, qualitative analysis shows that men and women differ substantially in the types of emojis they use and in their use of lengthened words.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aldihan-etal-2022-pilot">
<titleInfo>
<title>A Pilot Study on the Collection and Computational Analysis of Linguistic Differences Amongst Men and Women in a Kuwaiti Arabic WhatsApp Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hesah</namePart>
<namePart type="family">Aldihan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Gaizauskas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Susan</namePart>
<namePart type="family">Fitzmaurice</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>This study focuses on the collection and computational analysis of Kuwaiti Arabic (KA), which is considered a low resource dialect, to test different sociolinguistic hypotheses related to gendered language use. In this paper, we describe the collection and analysis of a corpus of WhatsApp Group chats with mixed gender Kuwaiti participants. This corpus, which we are making publicly available, is the first corpus of KA conversational data. We analyse different interactional and linguistic features to get insights about features that may be indicative of gender to inform the development of a gender classification system for KA in an upcoming study. Statistical analysis of our data shows that there is insufficient evidence to claim that there are significant differences amongst men and women with respect to number of turns, length of turns and number of emojis. However, qualitative analysis shows that men and women differ substantially in the types of emojis they use and in their use of lengthened words.</abstract>
<identifier type="citekey">aldihan-etal-2022-pilot</identifier>
<identifier type="doi">10.18653/v1/2022.wanlp-1.35</identifier>
<location>
<url>https://aclanthology.org/2022.wanlp-1.35</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>372</start>
<end>380</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Pilot Study on the Collection and Computational Analysis of Linguistic Differences Amongst Men and Women in a Kuwaiti Arabic WhatsApp Dataset
%A Aldihan, Hesah
%A Gaizauskas, Robert
%A Fitzmaurice, Susan
%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 aldihan-etal-2022-pilot
%X This study focuses on the collection and computational analysis of Kuwaiti Arabic (KA), which is considered a low resource dialect, to test different sociolinguistic hypotheses related to gendered language use. In this paper, we describe the collection and analysis of a corpus of WhatsApp Group chats with mixed gender Kuwaiti participants. This corpus, which we are making publicly available, is the first corpus of KA conversational data. We analyse different interactional and linguistic features to get insights about features that may be indicative of gender to inform the development of a gender classification system for KA in an upcoming study. Statistical analysis of our data shows that there is insufficient evidence to claim that there are significant differences amongst men and women with respect to number of turns, length of turns and number of emojis. However, qualitative analysis shows that men and women differ substantially in the types of emojis they use and in their use of lengthened words.
%R 10.18653/v1/2022.wanlp-1.35
%U https://aclanthology.org/2022.wanlp-1.35
%U https://doi.org/10.18653/v1/2022.wanlp-1.35
%P 372-380
Markdown (Informal)
[A Pilot Study on the Collection and Computational Analysis of Linguistic Differences Amongst Men and Women in a Kuwaiti Arabic WhatsApp Dataset](https://aclanthology.org/2022.wanlp-1.35) (Aldihan et al., WANLP 2022)
ACL