@inproceedings{fortuna-etal-2020-toxic,
title = "Toxic, Hateful, Offensive or Abusive? What Are We Really Classifying? An Empirical Analysis of Hate Speech Datasets",
author = "Fortuna, Paula and
Soler, Juan and
Wanner, Leo",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.838",
pages = "6786--6794",
abstract = "The field of the automatic detection of hate speech and related concepts has raised a lot of interest in the last years. Different datasets were annotated and classified by means of applying different machine learning algorithms. However, few efforts were done in order to clarify the applied categories and homogenize different datasets. Our study takes up this demand. We analyze six different publicly available datasets in this field with respect to their similarity and compatibility. We conduct two different experiments. First, we try to make the datasets compatible and represent the dataset classes as Fast Text word vectors analyzing the similarity between different classes in a intra and inter dataset manner. Second, we submit the chosen datasets to the Perspective API Toxicity classifier, achieving different performances depending on the categories and datasets. One of the main conclusions of these experiments is that many different definitions are being used for equivalent concepts, which makes most of the publicly available datasets incompatible. Grounded in our analysis, we provide guidelines for future dataset collection and annotation.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fortuna-etal-2020-toxic">
<titleInfo>
<title>Toxic, Hateful, Offensive or Abusive? What Are We Really Classifying? An Empirical Analysis of Hate Speech Datasets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paula</namePart>
<namePart type="family">Fortuna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Soler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>The field of the automatic detection of hate speech and related concepts has raised a lot of interest in the last years. Different datasets were annotated and classified by means of applying different machine learning algorithms. However, few efforts were done in order to clarify the applied categories and homogenize different datasets. Our study takes up this demand. We analyze six different publicly available datasets in this field with respect to their similarity and compatibility. We conduct two different experiments. First, we try to make the datasets compatible and represent the dataset classes as Fast Text word vectors analyzing the similarity between different classes in a intra and inter dataset manner. Second, we submit the chosen datasets to the Perspective API Toxicity classifier, achieving different performances depending on the categories and datasets. One of the main conclusions of these experiments is that many different definitions are being used for equivalent concepts, which makes most of the publicly available datasets incompatible. Grounded in our analysis, we provide guidelines for future dataset collection and annotation.</abstract>
<identifier type="citekey">fortuna-etal-2020-toxic</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.838</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6786</start>
<end>6794</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Toxic, Hateful, Offensive or Abusive? What Are We Really Classifying? An Empirical Analysis of Hate Speech Datasets
%A Fortuna, Paula
%A Soler, Juan
%A Wanner, Leo
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F fortuna-etal-2020-toxic
%X The field of the automatic detection of hate speech and related concepts has raised a lot of interest in the last years. Different datasets were annotated and classified by means of applying different machine learning algorithms. However, few efforts were done in order to clarify the applied categories and homogenize different datasets. Our study takes up this demand. We analyze six different publicly available datasets in this field with respect to their similarity and compatibility. We conduct two different experiments. First, we try to make the datasets compatible and represent the dataset classes as Fast Text word vectors analyzing the similarity between different classes in a intra and inter dataset manner. Second, we submit the chosen datasets to the Perspective API Toxicity classifier, achieving different performances depending on the categories and datasets. One of the main conclusions of these experiments is that many different definitions are being used for equivalent concepts, which makes most of the publicly available datasets incompatible. Grounded in our analysis, we provide guidelines for future dataset collection and annotation.
%U https://aclanthology.org/2020.lrec-1.838
%P 6786-6794
Markdown (Informal)
[Toxic, Hateful, Offensive or Abusive? What Are We Really Classifying? An Empirical Analysis of Hate Speech Datasets](https://aclanthology.org/2020.lrec-1.838) (Fortuna et al., LREC 2020)
ACL