@inproceedings{kums-etal-2025-novel,
title = "A Novel Dataset for Classifying {G}erman Hate Speech Comments with Criminal Relevance",
author = "Kums, Vincent and
Meyer, Florian and
Pivit, Luisa and
Vedenina, Uliana and
Wortmann, Jonas and
Siegel, Melanie and
Labudde, Dirk",
editor = "Calabrese, Agostina and
de Kock, Christine and
Nozza, Debora and
Plaza-del-Arco, Flor Miriam and
Talat, Zeerak and
Vargas, Francielle",
booktitle = "Proceedings of the The 9th Workshop on Online Abuse and Harms (WOAH)",
month = aug,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.woah-1.4/",
pages = "41--52",
ISBN = "979-8-89176-105-6",
abstract = "The consistently high prevalence of hate speech on the Internet continues to pose significant social and individual challenges. Given the centrality of social networks in public discourse, automating the identification of criminally relevant content is a pressing challenge. This study addresses the challenge of developing an automated system that is capable of classifying online comments in a criminal justice context and categorising them into relevant sections of the criminal code. Not only technical, but also ethical and legal requirements must be considered. To this end, 351 comments were annotated by public prosecutors from the Central Office for Combating Internet and Computer Crime (ZIT) according to previously formed paragraph classes. These groupings consist of several German criminal law statutes that most hate comments violate. In the subsequent phase of the research, a further 839 records were assigned to the classes by student annotators who had been trained previously."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kums-etal-2025-novel">
<titleInfo>
<title>A Novel Dataset for Classifying German Hate Speech Comments with Criminal Relevance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Kums</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Meyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luisa</namePart>
<namePart type="family">Pivit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uliana</namePart>
<namePart type="family">Vedenina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="family">Wortmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melanie</namePart>
<namePart type="family">Siegel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Labudde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the The 9th Workshop on Online Abuse and Harms (WOAH)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agostina</namePart>
<namePart type="family">Calabrese</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christine</namePart>
<namePart type="family">de Kock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debora</namePart>
<namePart type="family">Nozza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flor</namePart>
<namePart type="given">Miriam</namePart>
<namePart type="family">Plaza-del-Arco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeerak</namePart>
<namePart type="family">Talat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francielle</namePart>
<namePart type="family">Vargas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-105-6</identifier>
</relatedItem>
<abstract>The consistently high prevalence of hate speech on the Internet continues to pose significant social and individual challenges. Given the centrality of social networks in public discourse, automating the identification of criminally relevant content is a pressing challenge. This study addresses the challenge of developing an automated system that is capable of classifying online comments in a criminal justice context and categorising them into relevant sections of the criminal code. Not only technical, but also ethical and legal requirements must be considered. To this end, 351 comments were annotated by public prosecutors from the Central Office for Combating Internet and Computer Crime (ZIT) according to previously formed paragraph classes. These groupings consist of several German criminal law statutes that most hate comments violate. In the subsequent phase of the research, a further 839 records were assigned to the classes by student annotators who had been trained previously.</abstract>
<identifier type="citekey">kums-etal-2025-novel</identifier>
<location>
<url>https://aclanthology.org/2025.woah-1.4/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>41</start>
<end>52</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Novel Dataset for Classifying German Hate Speech Comments with Criminal Relevance
%A Kums, Vincent
%A Meyer, Florian
%A Pivit, Luisa
%A Vedenina, Uliana
%A Wortmann, Jonas
%A Siegel, Melanie
%A Labudde, Dirk
%Y Calabrese, Agostina
%Y de Kock, Christine
%Y Nozza, Debora
%Y Plaza-del-Arco, Flor Miriam
%Y Talat, Zeerak
%Y Vargas, Francielle
%S Proceedings of the The 9th Workshop on Online Abuse and Harms (WOAH)
%D 2025
%8 August
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-105-6
%F kums-etal-2025-novel
%X The consistently high prevalence of hate speech on the Internet continues to pose significant social and individual challenges. Given the centrality of social networks in public discourse, automating the identification of criminally relevant content is a pressing challenge. This study addresses the challenge of developing an automated system that is capable of classifying online comments in a criminal justice context and categorising them into relevant sections of the criminal code. Not only technical, but also ethical and legal requirements must be considered. To this end, 351 comments were annotated by public prosecutors from the Central Office for Combating Internet and Computer Crime (ZIT) according to previously formed paragraph classes. These groupings consist of several German criminal law statutes that most hate comments violate. In the subsequent phase of the research, a further 839 records were assigned to the classes by student annotators who had been trained previously.
%U https://aclanthology.org/2025.woah-1.4/
%P 41-52
Markdown (Informal)
[A Novel Dataset for Classifying German Hate Speech Comments with Criminal Relevance](https://aclanthology.org/2025.woah-1.4/) (Kums et al., WOAH 2025)
ACL