@inproceedings{arora-etal-2024-uli,
title = "The Uli Dataset: An Exercise in Experience Led Annotation of o{GBV}",
author = "Arora, Arnav and
Jinadoss, Maha and
Arora, Cheshta and
George, Denny and
{Brindaalakshmi} and
Khan, Haseena and
Rawat, Kirti and
{Div} and
{Ritash} and
Mathur, Seema",
editor = {Chung, Yi-Ling and
Talat, Zeerak and
Nozza, Debora and
Plaza-del-Arco, Flor Miriam and
R{\"o}ttger, Paul and
Mostafazadeh Davani, Aida and
Calabrese, Agostina},
booktitle = "Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.woah-1.16",
doi = "10.18653/v1/2024.woah-1.16",
pages = "212--222",
abstract = "Online gender-based violence has grown concomitantly with the adoption of the internet and social media. Its effects are worse in the Global majority where many users use social media in languages other than English. The scale and volume of conversations on the internet have necessitated the need for automated detection of hate speech and, more specifically, gendered abuse. There is, however, a lack of language-specific and contextual data to build such automated tools. In this paper, we present a dataset on gendered abuse in three languages- Hindi, Tamil and Indian English. The dataset comprises of tweets annotated along three questions pertaining to the experience of gender abuse, by experts who identify as women or a member of the LGBTQIA+ community in South Asia. Through this dataset, we demonstrate a participatory approach to creating datasets that drive AI systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arora-etal-2024-uli">
<titleInfo>
<title>The Uli Dataset: An Exercise in Experience Led Annotation of oGBV</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arnav</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maha</namePart>
<namePart type="family">Jinadoss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheshta</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Denny</namePart>
<namePart type="family">George</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name>
<namePart>Brindaalakshmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haseena</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirti</namePart>
<namePart type="family">Rawat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name>
<namePart>Div</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name>
<namePart>Ritash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seema</namePart>
<namePart type="family">Mathur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yi-Ling</namePart>
<namePart type="family">Chung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeerak</namePart>
<namePart type="family">Talat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debora</namePart>
<namePart type="family">Nozza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flor</namePart>
<namePart type="given">Miriam</namePart>
<namePart type="family">Plaza-del-Arco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Röttger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aida</namePart>
<namePart type="family">Mostafazadeh Davani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agostina</namePart>
<namePart type="family">Calabrese</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Online gender-based violence has grown concomitantly with the adoption of the internet and social media. Its effects are worse in the Global majority where many users use social media in languages other than English. The scale and volume of conversations on the internet have necessitated the need for automated detection of hate speech and, more specifically, gendered abuse. There is, however, a lack of language-specific and contextual data to build such automated tools. In this paper, we present a dataset on gendered abuse in three languages- Hindi, Tamil and Indian English. The dataset comprises of tweets annotated along three questions pertaining to the experience of gender abuse, by experts who identify as women or a member of the LGBTQIA+ community in South Asia. Through this dataset, we demonstrate a participatory approach to creating datasets that drive AI systems.</abstract>
<identifier type="citekey">arora-etal-2024-uli</identifier>
<identifier type="doi">10.18653/v1/2024.woah-1.16</identifier>
<location>
<url>https://aclanthology.org/2024.woah-1.16</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>212</start>
<end>222</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Uli Dataset: An Exercise in Experience Led Annotation of oGBV
%A Arora, Arnav
%A Jinadoss, Maha
%A Arora, Cheshta
%A George, Denny
%A Khan, Haseena
%A Rawat, Kirti
%A Mathur, Seema
%Y Chung, Yi-Ling
%Y Talat, Zeerak
%Y Nozza, Debora
%Y Plaza-del-Arco, Flor Miriam
%Y Röttger, Paul
%Y Mostafazadeh Davani, Aida
%Y Calabrese, Agostina
%A Brindaalakshmi
%A Div
%A Ritash
%S Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F arora-etal-2024-uli
%X Online gender-based violence has grown concomitantly with the adoption of the internet and social media. Its effects are worse in the Global majority where many users use social media in languages other than English. The scale and volume of conversations on the internet have necessitated the need for automated detection of hate speech and, more specifically, gendered abuse. There is, however, a lack of language-specific and contextual data to build such automated tools. In this paper, we present a dataset on gendered abuse in three languages- Hindi, Tamil and Indian English. The dataset comprises of tweets annotated along three questions pertaining to the experience of gender abuse, by experts who identify as women or a member of the LGBTQIA+ community in South Asia. Through this dataset, we demonstrate a participatory approach to creating datasets that drive AI systems.
%R 10.18653/v1/2024.woah-1.16
%U https://aclanthology.org/2024.woah-1.16
%U https://doi.org/10.18653/v1/2024.woah-1.16
%P 212-222
Markdown (Informal)
[The Uli Dataset: An Exercise in Experience Led Annotation of oGBV](https://aclanthology.org/2024.woah-1.16) (Arora et al., WOAH-WS 2024)
ACL
- Arnav Arora, Maha Jinadoss, Cheshta Arora, Denny George, Brindaalakshmi, Haseena Khan, Kirti Rawat, Div, Ritash, and Seema Mathur. 2024. The Uli Dataset: An Exercise in Experience Led Annotation of oGBV. In Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024), pages 212–222, Mexico City, Mexico. Association for Computational Linguistics.