@inproceedings{mosca-etal-2021-understanding,
title = "Understanding and Interpreting the Impact of User Context in Hate Speech Detection",
author = "Mosca, Edoardo and
Wich, Maximilian and
Groh, Georg",
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-1.8",
doi = "10.18653/v1/2021.socialnlp-1.8",
pages = "91--102",
abstract = "As hate speech spreads on social media and online communities, research continues to work on its automatic detection. Recently, recognition performance has been increasing thanks to advances in deep learning and the integration of user features. This work investigates the effects that such features can have on a detection model. Unlike previous research, we show that simple performance comparison does not expose the full impact of including contextual- and user information. By leveraging explainability techniques, we show (1) that user features play a role in the model{'}s decision and (2) how they affect the feature space learned by the model. Besides revealing that{---}and also illustrating why{---}user features are the reason for performance gains, we show how such techniques can be combined to better understand the model and to detect unintended bias.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mosca-etal-2021-understanding">
<titleInfo>
<title>Understanding and Interpreting the Impact of User Context in Hate Speech Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Edoardo</namePart>
<namePart type="family">Mosca</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maximilian</namePart>
<namePart type="family">Wich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Groh</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>As hate speech spreads on social media and online communities, research continues to work on its automatic detection. Recently, recognition performance has been increasing thanks to advances in deep learning and the integration of user features. This work investigates the effects that such features can have on a detection model. Unlike previous research, we show that simple performance comparison does not expose the full impact of including contextual- and user information. By leveraging explainability techniques, we show (1) that user features play a role in the model’s decision and (2) how they affect the feature space learned by the model. Besides revealing that—and also illustrating why—user features are the reason for performance gains, we show how such techniques can be combined to better understand the model and to detect unintended bias.</abstract>
<identifier type="citekey">mosca-etal-2021-understanding</identifier>
<identifier type="doi">10.18653/v1/2021.socialnlp-1.8</identifier>
<location>
<url>https://aclanthology.org/2021.socialnlp-1.8</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>91</start>
<end>102</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Understanding and Interpreting the Impact of User Context in Hate Speech Detection
%A Mosca, Edoardo
%A Wich, Maximilian
%A Groh, Georg
%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 mosca-etal-2021-understanding
%X As hate speech spreads on social media and online communities, research continues to work on its automatic detection. Recently, recognition performance has been increasing thanks to advances in deep learning and the integration of user features. This work investigates the effects that such features can have on a detection model. Unlike previous research, we show that simple performance comparison does not expose the full impact of including contextual- and user information. By leveraging explainability techniques, we show (1) that user features play a role in the model’s decision and (2) how they affect the feature space learned by the model. Besides revealing that—and also illustrating why—user features are the reason for performance gains, we show how such techniques can be combined to better understand the model and to detect unintended bias.
%R 10.18653/v1/2021.socialnlp-1.8
%U https://aclanthology.org/2021.socialnlp-1.8
%U https://doi.org/10.18653/v1/2021.socialnlp-1.8
%P 91-102
Markdown (Informal)
[Understanding and Interpreting the Impact of User Context in Hate Speech Detection](https://aclanthology.org/2021.socialnlp-1.8) (Mosca et al., SocialNLP 2021)
ACL