@inproceedings{larimore-etal-2021-reconsidering,
title = "Reconsidering Annotator Disagreement about Racist Language: Noise or Signal?",
author = "Larimore, Savannah and
Kennedy, Ian and
Haskett, Breon and
Arseniev-Koehler, Alina",
editor = "Ku, Lun-Wei and
Li, Cheng-Te",
booktitle = "Proceedings of the Ninth International Workshop on Natural Language Processing for Social Media",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.socialnlp-1.7",
doi = "10.18653/v1/2021.socialnlp-1.7",
pages = "81--90",
abstract = "An abundance of methodological work aims to detect hateful and racist language in text. However, these tools are hampered by problems like low annotator agreement and remain largely disconnected from theoretical work on race and racism in the social sciences. Using annotations of 5188 tweets from 291 annotators, we investigate how annotator perceptions of racism in tweets vary by annotator racial identity and two text features of the tweets: relevant keywords and latent topics identified through structural topic modeling. We provide a descriptive summary of our data and estimate a series of generalized linear models to determine if annotator racial identity and our 12 latent topics, alone or in combination, explain the way racial sentiment was annotated, net of relevant annotator characteristics and tweet features. Our results show that White and non-White annotators exhibit significant differences in ratings when reading tweets with high prevalence of particular, racially-charged topics. We conclude by suggesting how future methodological work can draw on our results and further incorporate social science theory into analyses.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="larimore-etal-2021-reconsidering">
<titleInfo>
<title>Reconsidering Annotator Disagreement about Racist Language: Noise or Signal?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Savannah</namePart>
<namePart type="family">Larimore</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ian</namePart>
<namePart type="family">Kennedy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Breon</namePart>
<namePart type="family">Haskett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Arseniev-Koehler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Workshop on Natural Language Processing for Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheng-Te</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>An abundance of methodological work aims to detect hateful and racist language in text. However, these tools are hampered by problems like low annotator agreement and remain largely disconnected from theoretical work on race and racism in the social sciences. Using annotations of 5188 tweets from 291 annotators, we investigate how annotator perceptions of racism in tweets vary by annotator racial identity and two text features of the tweets: relevant keywords and latent topics identified through structural topic modeling. We provide a descriptive summary of our data and estimate a series of generalized linear models to determine if annotator racial identity and our 12 latent topics, alone or in combination, explain the way racial sentiment was annotated, net of relevant annotator characteristics and tweet features. Our results show that White and non-White annotators exhibit significant differences in ratings when reading tweets with high prevalence of particular, racially-charged topics. We conclude by suggesting how future methodological work can draw on our results and further incorporate social science theory into analyses.</abstract>
<identifier type="citekey">larimore-etal-2021-reconsidering</identifier>
<identifier type="doi">10.18653/v1/2021.socialnlp-1.7</identifier>
<location>
<url>https://aclanthology.org/2021.socialnlp-1.7</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>81</start>
<end>90</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reconsidering Annotator Disagreement about Racist Language: Noise or Signal?
%A Larimore, Savannah
%A Kennedy, Ian
%A Haskett, Breon
%A Arseniev-Koehler, Alina
%Y Ku, Lun-Wei
%Y Li, Cheng-Te
%S Proceedings of the Ninth International Workshop on Natural Language Processing for Social Media
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F larimore-etal-2021-reconsidering
%X An abundance of methodological work aims to detect hateful and racist language in text. However, these tools are hampered by problems like low annotator agreement and remain largely disconnected from theoretical work on race and racism in the social sciences. Using annotations of 5188 tweets from 291 annotators, we investigate how annotator perceptions of racism in tweets vary by annotator racial identity and two text features of the tweets: relevant keywords and latent topics identified through structural topic modeling. We provide a descriptive summary of our data and estimate a series of generalized linear models to determine if annotator racial identity and our 12 latent topics, alone or in combination, explain the way racial sentiment was annotated, net of relevant annotator characteristics and tweet features. Our results show that White and non-White annotators exhibit significant differences in ratings when reading tweets with high prevalence of particular, racially-charged topics. We conclude by suggesting how future methodological work can draw on our results and further incorporate social science theory into analyses.
%R 10.18653/v1/2021.socialnlp-1.7
%U https://aclanthology.org/2021.socialnlp-1.7
%U https://doi.org/10.18653/v1/2021.socialnlp-1.7
%P 81-90
Markdown (Informal)
[Reconsidering Annotator Disagreement about Racist Language: Noise or Signal?](https://aclanthology.org/2021.socialnlp-1.7) (Larimore et al., SocialNLP 2021)
ACL