@inproceedings{van-dorpe-etal-2023-unveiling,
title = "Unveiling Identity Biases in Toxicity Detection : A Game-Focused Dataset and Reactivity Analysis Approach",
author = "Van Dorpe, Josiane and
Yang, Zachary and
Grenon-Godbout, Nicolas and
Winterstein, Gr{\'e}goire",
editor = "Wang, Mingxuan and
Zitouni, Imed",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-industry.26",
doi = "10.18653/v1/2023.emnlp-industry.26",
pages = "263--274",
abstract = "Identity biases arise commonly from annotated datasets, can be propagated in language models and can cause further harm to marginal groups. Existing bias benchmarking datasets are mainly focused on gender or racial biases and are made to pinpoint which class the model is biased towards. They also are not designed for the gaming industry, a concern for models built for toxicity detection in videogames{'} chat. We propose a dataset and a method to highlight oversensitive terms using reactivity analysis and the model{'}s performance. We test our dataset against ToxBuster, a language model developed by Ubisoft fine-tuned for toxicity detection on multiplayer videogame{'}s written chat, and Perspective API. We find that these toxicity models often automatically tag terms related to a community{'}s identity as toxic, which prevents members of already marginalized groups to make their presence known or have a mature / normal conversation. Through this process, we have generated an interesting list of terms that trigger the models to varying degrees, along with insights on establishing a baseline through human annotations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-dorpe-etal-2023-unveiling">
<titleInfo>
<title>Unveiling Identity Biases in Toxicity Detection : A Game-Focused Dataset and Reactivity Analysis Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Josiane</namePart>
<namePart type="family">Van Dorpe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zachary</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Grenon-Godbout</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grégoire</namePart>
<namePart type="family">Winterstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mingxuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Identity biases arise commonly from annotated datasets, can be propagated in language models and can cause further harm to marginal groups. Existing bias benchmarking datasets are mainly focused on gender or racial biases and are made to pinpoint which class the model is biased towards. They also are not designed for the gaming industry, a concern for models built for toxicity detection in videogames’ chat. We propose a dataset and a method to highlight oversensitive terms using reactivity analysis and the model’s performance. We test our dataset against ToxBuster, a language model developed by Ubisoft fine-tuned for toxicity detection on multiplayer videogame’s written chat, and Perspective API. We find that these toxicity models often automatically tag terms related to a community’s identity as toxic, which prevents members of already marginalized groups to make their presence known or have a mature / normal conversation. Through this process, we have generated an interesting list of terms that trigger the models to varying degrees, along with insights on establishing a baseline through human annotations.</abstract>
<identifier type="citekey">van-dorpe-etal-2023-unveiling</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-industry.26</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-industry.26</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>263</start>
<end>274</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unveiling Identity Biases in Toxicity Detection : A Game-Focused Dataset and Reactivity Analysis Approach
%A Van Dorpe, Josiane
%A Yang, Zachary
%A Grenon-Godbout, Nicolas
%A Winterstein, Grégoire
%Y Wang, Mingxuan
%Y Zitouni, Imed
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F van-dorpe-etal-2023-unveiling
%X Identity biases arise commonly from annotated datasets, can be propagated in language models and can cause further harm to marginal groups. Existing bias benchmarking datasets are mainly focused on gender or racial biases and are made to pinpoint which class the model is biased towards. They also are not designed for the gaming industry, a concern for models built for toxicity detection in videogames’ chat. We propose a dataset and a method to highlight oversensitive terms using reactivity analysis and the model’s performance. We test our dataset against ToxBuster, a language model developed by Ubisoft fine-tuned for toxicity detection on multiplayer videogame’s written chat, and Perspective API. We find that these toxicity models often automatically tag terms related to a community’s identity as toxic, which prevents members of already marginalized groups to make their presence known or have a mature / normal conversation. Through this process, we have generated an interesting list of terms that trigger the models to varying degrees, along with insights on establishing a baseline through human annotations.
%R 10.18653/v1/2023.emnlp-industry.26
%U https://aclanthology.org/2023.emnlp-industry.26
%U https://doi.org/10.18653/v1/2023.emnlp-industry.26
%P 263-274
Markdown (Informal)
[Unveiling Identity Biases in Toxicity Detection : A Game-Focused Dataset and Reactivity Analysis Approach](https://aclanthology.org/2023.emnlp-industry.26) (Van Dorpe et al., EMNLP 2023)
ACL