@inproceedings{markov-daelemans-2021-improving,
title = "Improving Cross-Domain Hate Speech Detection by Reducing the False Positive Rate",
author = "Markov, Ilia and
Daelemans, Walter",
editor = "Feldman, Anna and
Da San Martino, Giovanni and
Leberknight, Chris and
Nakov, Preslav",
booktitle = "Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.nlp4if-1.3/",
doi = "10.18653/v1/2021.nlp4if-1.3",
pages = "17--22",
abstract = "Hate speech detection is an actively growing field of research with a variety of recently proposed approaches that allowed to push the state-of-the-art results. One of the challenges of such automated approaches {--} namely recent deep learning models {--} is a risk of false positives (i.e., false accusations), which may lead to over-blocking or removal of harmless social media content in applications with little moderator intervention. We evaluate deep learning models both under in-domain and cross-domain hate speech detection conditions, and introduce an SVM approach that allows to significantly improve the state-of-the-art results when combined with the deep learning models through a simple majority-voting ensemble. The improvement is mainly due to a reduction of the false positive rate."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="markov-daelemans-2021-improving">
<titleInfo>
<title>Improving Cross-Domain Hate Speech Detection by Reducing the False Positive Rate</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ilia</namePart>
<namePart type="family">Markov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walter</namePart>
<namePart type="family">Daelemans</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 Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Feldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Leberknight</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</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>Hate speech detection is an actively growing field of research with a variety of recently proposed approaches that allowed to push the state-of-the-art results. One of the challenges of such automated approaches – namely recent deep learning models – is a risk of false positives (i.e., false accusations), which may lead to over-blocking or removal of harmless social media content in applications with little moderator intervention. We evaluate deep learning models both under in-domain and cross-domain hate speech detection conditions, and introduce an SVM approach that allows to significantly improve the state-of-the-art results when combined with the deep learning models through a simple majority-voting ensemble. The improvement is mainly due to a reduction of the false positive rate.</abstract>
<identifier type="citekey">markov-daelemans-2021-improving</identifier>
<identifier type="doi">10.18653/v1/2021.nlp4if-1.3</identifier>
<location>
<url>https://aclanthology.org/2021.nlp4if-1.3/</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>17</start>
<end>22</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Cross-Domain Hate Speech Detection by Reducing the False Positive Rate
%A Markov, Ilia
%A Daelemans, Walter
%Y Feldman, Anna
%Y Da San Martino, Giovanni
%Y Leberknight, Chris
%Y Nakov, Preslav
%S Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F markov-daelemans-2021-improving
%X Hate speech detection is an actively growing field of research with a variety of recently proposed approaches that allowed to push the state-of-the-art results. One of the challenges of such automated approaches – namely recent deep learning models – is a risk of false positives (i.e., false accusations), which may lead to over-blocking or removal of harmless social media content in applications with little moderator intervention. We evaluate deep learning models both under in-domain and cross-domain hate speech detection conditions, and introduce an SVM approach that allows to significantly improve the state-of-the-art results when combined with the deep learning models through a simple majority-voting ensemble. The improvement is mainly due to a reduction of the false positive rate.
%R 10.18653/v1/2021.nlp4if-1.3
%U https://aclanthology.org/2021.nlp4if-1.3/
%U https://doi.org/10.18653/v1/2021.nlp4if-1.3
%P 17-22
Markdown (Informal)
[Improving Cross-Domain Hate Speech Detection by Reducing the False Positive Rate](https://aclanthology.org/2021.nlp4if-1.3/) (Markov & Daelemans, NLP4IF 2021)
ACL