@inproceedings{mubarak-etal-2022-arabgend,
title = "{A}rab{G}end: Gender Analysis and Inference on {A}rabic {T}witter",
author = "Mubarak, Hamdy and
Chowdhury, Shammur Absar and
Alam, Firoj",
booktitle = "Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022)",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.wnut-1.14",
pages = "124--135",
abstract = "Gender analysis of Twitter can reveal important socio-cultural differences between male and female users. There has been a significant effort to analyze and automatically infer gender in the past for most widely spoken languages{'} content, however, to our knowledge very limited work has been done for Arabic. In this paper, we perform an extensive analysis of differences between male and female users on the Arabic Twitter-sphere. We study differences in user engagement, topics of interest, and the gender gap in professions. Along with gender analysis, we also propose a method to infer gender by utilizing usernames, profile pictures, tweets, and networks of friends. In order to do so, we manually annotated gender and locations for {\textasciitilde}166K Twitter accounts associated with {\textasciitilde}92K user location, which we plan to make publicly available. Our proposed gender inference method achieve an F1 score of 82.1{\%} (47.3{\%} higher than majority baseline). We also developed a demo and made it publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mubarak-etal-2022-arabgend">
<titleInfo>
<title>ArabGend: Gender Analysis and Inference on Arabic Twitter</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hamdy</namePart>
<namePart type="family">Mubarak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shammur</namePart>
<namePart type="given">Absar</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Gender analysis of Twitter can reveal important socio-cultural differences between male and female users. There has been a significant effort to analyze and automatically infer gender in the past for most widely spoken languages’ content, however, to our knowledge very limited work has been done for Arabic. In this paper, we perform an extensive analysis of differences between male and female users on the Arabic Twitter-sphere. We study differences in user engagement, topics of interest, and the gender gap in professions. Along with gender analysis, we also propose a method to infer gender by utilizing usernames, profile pictures, tweets, and networks of friends. In order to do so, we manually annotated gender and locations for ~166K Twitter accounts associated with ~92K user location, which we plan to make publicly available. Our proposed gender inference method achieve an F1 score of 82.1% (47.3% higher than majority baseline). We also developed a demo and made it publicly available.</abstract>
<identifier type="citekey">mubarak-etal-2022-arabgend</identifier>
<location>
<url>https://aclanthology.org/2022.wnut-1.14</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>124</start>
<end>135</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ArabGend: Gender Analysis and Inference on Arabic Twitter
%A Mubarak, Hamdy
%A Chowdhury, Shammur Absar
%A Alam, Firoj
%S Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022)
%D 2022
%8 October
%I Association for Computational Linguistics
%C Gyeongju, Republic of Korea
%F mubarak-etal-2022-arabgend
%X Gender analysis of Twitter can reveal important socio-cultural differences between male and female users. There has been a significant effort to analyze and automatically infer gender in the past for most widely spoken languages’ content, however, to our knowledge very limited work has been done for Arabic. In this paper, we perform an extensive analysis of differences between male and female users on the Arabic Twitter-sphere. We study differences in user engagement, topics of interest, and the gender gap in professions. Along with gender analysis, we also propose a method to infer gender by utilizing usernames, profile pictures, tweets, and networks of friends. In order to do so, we manually annotated gender and locations for ~166K Twitter accounts associated with ~92K user location, which we plan to make publicly available. Our proposed gender inference method achieve an F1 score of 82.1% (47.3% higher than majority baseline). We also developed a demo and made it publicly available.
%U https://aclanthology.org/2022.wnut-1.14
%P 124-135
Markdown (Informal)
[ArabGend: Gender Analysis and Inference on Arabic Twitter](https://aclanthology.org/2022.wnut-1.14) (Mubarak et al., WNUT 2022)
ACL
- Hamdy Mubarak, Shammur Absar Chowdhury, and Firoj Alam. 2022. ArabGend: Gender Analysis and Inference on Arabic Twitter. In Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022), pages 124–135, Gyeongju, Republic of Korea. Association for Computational Linguistics.