@inproceedings{engelmann-etal-2024-dataset,
title = "A Dataset for the Detection of Dehumanizing Language",
author = "Engelmann, Paul and
Trolle, Peter and
Hardmeier, Christian",
editor = {Chakravarthi, Bharathi Raja and
B, Bharathi and
Buitelaar, Paul and
Durairaj, Thenmozhi and
Kov{\'a}cs, Gy{\"o}rgy and
Garc{\'\i}a Cumbreras, Miguel {\'A}ngel},
booktitle = "Proceedings of the Fourth Workshop on Language Technology for Equality, Diversity, Inclusion",
month = mar,
year = "2024",
address = "St. Julian's, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.ltedi-1.2",
pages = "14--20",
abstract = "Dehumanization is a mental process that enables the exclusion and ill treatment of a group of people. In this paper, we present two data sets of dehumanizing text, a large, automatically collected corpus and a smaller, manually annotated data set. Both data sets include a combination of political discourse and dialogue from movie subtitles. Our methods give us a broad and varied amount of dehumanization data to work with, enabling further exploratory analysis as well as automatic classification of dehumanization patterns. Both data sets will be publicly released.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="engelmann-etal-2024-dataset">
<titleInfo>
<title>A Dataset for the Detection of Dehumanizing Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Engelmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Trolle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Hardmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Language Technology for Equality, Diversity, Inclusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="family">B</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Buitelaar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thenmozhi</namePart>
<namePart type="family">Durairaj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">György</namePart>
<namePart type="family">Kovács</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="given">Ángel</namePart>
<namePart type="family">García Cumbreras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Dehumanization is a mental process that enables the exclusion and ill treatment of a group of people. In this paper, we present two data sets of dehumanizing text, a large, automatically collected corpus and a smaller, manually annotated data set. Both data sets include a combination of political discourse and dialogue from movie subtitles. Our methods give us a broad and varied amount of dehumanization data to work with, enabling further exploratory analysis as well as automatic classification of dehumanization patterns. Both data sets will be publicly released.</abstract>
<identifier type="citekey">engelmann-etal-2024-dataset</identifier>
<location>
<url>https://aclanthology.org/2024.ltedi-1.2</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>14</start>
<end>20</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Dataset for the Detection of Dehumanizing Language
%A Engelmann, Paul
%A Trolle, Peter
%A Hardmeier, Christian
%Y Chakravarthi, Bharathi Raja
%Y B, Bharathi
%Y Buitelaar, Paul
%Y Durairaj, Thenmozhi
%Y Kovács, György
%Y García Cumbreras, Miguel Ángel
%S Proceedings of the Fourth Workshop on Language Technology for Equality, Diversity, Inclusion
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F engelmann-etal-2024-dataset
%X Dehumanization is a mental process that enables the exclusion and ill treatment of a group of people. In this paper, we present two data sets of dehumanizing text, a large, automatically collected corpus and a smaller, manually annotated data set. Both data sets include a combination of political discourse and dialogue from movie subtitles. Our methods give us a broad and varied amount of dehumanization data to work with, enabling further exploratory analysis as well as automatic classification of dehumanization patterns. Both data sets will be publicly released.
%U https://aclanthology.org/2024.ltedi-1.2
%P 14-20
Markdown (Informal)
[A Dataset for the Detection of Dehumanizing Language](https://aclanthology.org/2024.ltedi-1.2) (Engelmann et al., LTEDI-WS 2024)
ACL
- Paul Engelmann, Peter Trolle, and Christian Hardmeier. 2024. A Dataset for the Detection of Dehumanizing Language. In Proceedings of the Fourth Workshop on Language Technology for Equality, Diversity, Inclusion, pages 14–20, St. Julian's, Malta. Association for Computational Linguistics.