Who are the haters? A corpus-based demographic analysis of authors of hate speech

Lisa Hilte; Ilia Markov; Nikola Ljubešić; Darja Fišer; Walter Daelemans

doi:10.3389/frai.2023.986890

Who are the haters? A corpus-based demographic analysis of authors of hate speech

Lisa Hilte^*, Ilia Markov, Nikola Ljubešić, Darja Fišer, Walter Daelemans

^*Corresponding author for this work

Research output: Contribution to Journal › Article › Academic › peer-review

Abstract

Introduction: We examine the profiles of hate speech authors in a multilingual dataset of Facebook reactions to news posts discussing topics related to migrants and the LGBT+ community. The included languages are English, Dutch, Slovenian, and Croatian. Methods: First, all utterances were manually annotated as hateful or acceptable speech. Next, we used binary logistic regression to inspect how the production of hateful comments is impacted by authors' profiles (i.e., their age, gender, and language). Results: Our results corroborate previous findings: in all four languages, men produce more hateful comments than women, and people produce more hate speech as they grow older. But our findings also add important nuance to previously attested tendencies: specific age and gender dynamics vary slightly in different languages or cultures, suggesting that distinct (e.g., socio-political) realities are at play. Discussion: Finally, we discuss why author demographics are important in the study of hate speech: the profiles of prototypical “haters” can be used for hate speech detection, for sensibilization on and for counter-initiatives to the spread of (online) hatred.

Original language	English
Article number	986890
Pages (from-to)	1-12
Number of pages	12
Journal	Frontiers in Artificial Intelligence
Volume	6
DOIs	https://doi.org/10.3389/frai.2023.986890
Publication status	Published - 19 May 2023

Bibliographical note

Funding Information:
This work has been supported by the Slovenian Research Agency (ARRS) and the Flemish Research Foundation (FWO) through the bilateral research project ARRS N06-0099 and FWO G070619N LiLaH: Linguistic landscape of hate speech on social media; by the ARRS research core funding No. P6-0411 Language resources and technologies for Slovene language; the European Union's Rights, Equality and Citizenship Programme (2014-2020) project IMSyPP (Grant No. 875263); and the ARRS projects P6-0436 Digital Humanities: Resources, tools and methods, P6-0215 Slovene Language: Basic, Cognitive and Applied Studies, J5-3102 Hate speech in contemporary conceptualizations of nationalism, racism, gender and migration, and J7-4642 Basic research for the development of spoken language resources and speech technologies for the Slovenian language.

Publisher Copyright:
Copyright © 2023 Hilte, Markov, Ljubešić, Fišer and Daelemans.

Funding

This work has been supported by the Slovenian Research Agency (ARRS) and the Flemish Research Foundation (FWO) through the bilateral research project ARRS N06-0099 and FWO G070619N LiLaH: Linguistic landscape of hate speech on social media; by the ARRS research core funding No. P6-0411 Language resources and technologies for Slovene language; the European Union's Rights, Equality and Citizenship Programme (2014-2020) project IMSyPP (Grant No. 875263); and the ARRS projects P6-0436 Digital Humanities: Resources, tools and methods, P6-0215 Slovene Language: Basic, Cognitive and Applied Studies, J5-3102 Hate speech in contemporary conceptualizations of nationalism, racism, gender and migration, and J7-4642 Basic research for the development of spoken language resources and speech technologies for the Slovenian language.

Funders	Funder number
Fonds Wetenschappelijk Onderzoek	ARRS N06-0099, P6-0411, P6-0215, 875263, P6-0436, J7-4642
Javna Agencija za Raziskovalno Dejavnost RS

Keywords

age
demographics
gender
hate speech
language area

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.3389/frai.2023.986890

Persistent URL (handle)

Persistent link

Cite this

@article{bfba2a0043604f549fdfc34ae8738837,

title = "Who are the haters? A corpus-based demographic analysis of authors of hate speech",

abstract = "Introduction: We examine the profiles of hate speech authors in a multilingual dataset of Facebook reactions to news posts discussing topics related to migrants and the LGBT+ community. The included languages are English, Dutch, Slovenian, and Croatian. Methods: First, all utterances were manually annotated as hateful or acceptable speech. Next, we used binary logistic regression to inspect how the production of hateful comments is impacted by authors' profiles (i.e., their age, gender, and language). Results: Our results corroborate previous findings: in all four languages, men produce more hateful comments than women, and people produce more hate speech as they grow older. But our findings also add important nuance to previously attested tendencies: specific age and gender dynamics vary slightly in different languages or cultures, suggesting that distinct (e.g., socio-political) realities are at play. Discussion: Finally, we discuss why author demographics are important in the study of hate speech: the profiles of prototypical “haters” can be used for hate speech detection, for sensibilization on and for counter-initiatives to the spread of (online) hatred.",

keywords = "age, demographics, gender, hate speech, language area",

author = "Lisa Hilte and Ilia Markov and Nikola Ljube{\v s}i{\'c} and Darja Fi{\v s}er and Walter Daelemans",

note = "Funding Information: This work has been supported by the Slovenian Research Agency (ARRS) and the Flemish Research Foundation (FWO) through the bilateral research project ARRS N06-0099 and FWO G070619N LiLaH: Linguistic landscape of hate speech on social media; by the ARRS research core funding No. P6-0411 Language resources and technologies for Slovene language; the European Union's Rights, Equality and Citizenship Programme (2014-2020) project IMSyPP (Grant No. 875263); and the ARRS projects P6-0436 Digital Humanities: Resources, tools and methods, P6-0215 Slovene Language: Basic, Cognitive and Applied Studies, J5-3102 Hate speech in contemporary conceptualizations of nationalism, racism, gender and migration, and J7-4642 Basic research for the development of spoken language resources and speech technologies for the Slovenian language. Publisher Copyright: Copyright {\textcopyright} 2023 Hilte, Markov, Ljube{\v s}i{\'c}, Fi{\v s}er and Daelemans.",

year = "2023",

month = may,

day = "19",

doi = "10.3389/frai.2023.986890",

language = "English",

volume = "6",

pages = "1--12",

journal = "Frontiers in Artificial Intelligence",

issn = "2624-8212",

publisher = "Frontiers Media SA",

}

TY - JOUR

T1 - Who are the haters? A corpus-based demographic analysis of authors of hate speech

AU - Hilte, Lisa

AU - Markov, Ilia

AU - Ljubešić, Nikola

AU - Fišer, Darja

AU - Daelemans, Walter

N1 - Funding Information: This work has been supported by the Slovenian Research Agency (ARRS) and the Flemish Research Foundation (FWO) through the bilateral research project ARRS N06-0099 and FWO G070619N LiLaH: Linguistic landscape of hate speech on social media; by the ARRS research core funding No. P6-0411 Language resources and technologies for Slovene language; the European Union's Rights, Equality and Citizenship Programme (2014-2020) project IMSyPP (Grant No. 875263); and the ARRS projects P6-0436 Digital Humanities: Resources, tools and methods, P6-0215 Slovene Language: Basic, Cognitive and Applied Studies, J5-3102 Hate speech in contemporary conceptualizations of nationalism, racism, gender and migration, and J7-4642 Basic research for the development of spoken language resources and speech technologies for the Slovenian language. Publisher Copyright: Copyright © 2023 Hilte, Markov, Ljubešić, Fišer and Daelemans.

PY - 2023/5/19

Y1 - 2023/5/19

N2 - Introduction: We examine the profiles of hate speech authors in a multilingual dataset of Facebook reactions to news posts discussing topics related to migrants and the LGBT+ community. The included languages are English, Dutch, Slovenian, and Croatian. Methods: First, all utterances were manually annotated as hateful or acceptable speech. Next, we used binary logistic regression to inspect how the production of hateful comments is impacted by authors' profiles (i.e., their age, gender, and language). Results: Our results corroborate previous findings: in all four languages, men produce more hateful comments than women, and people produce more hate speech as they grow older. But our findings also add important nuance to previously attested tendencies: specific age and gender dynamics vary slightly in different languages or cultures, suggesting that distinct (e.g., socio-political) realities are at play. Discussion: Finally, we discuss why author demographics are important in the study of hate speech: the profiles of prototypical “haters” can be used for hate speech detection, for sensibilization on and for counter-initiatives to the spread of (online) hatred.

AB - Introduction: We examine the profiles of hate speech authors in a multilingual dataset of Facebook reactions to news posts discussing topics related to migrants and the LGBT+ community. The included languages are English, Dutch, Slovenian, and Croatian. Methods: First, all utterances were manually annotated as hateful or acceptable speech. Next, we used binary logistic regression to inspect how the production of hateful comments is impacted by authors' profiles (i.e., their age, gender, and language). Results: Our results corroborate previous findings: in all four languages, men produce more hateful comments than women, and people produce more hate speech as they grow older. But our findings also add important nuance to previously attested tendencies: specific age and gender dynamics vary slightly in different languages or cultures, suggesting that distinct (e.g., socio-political) realities are at play. Discussion: Finally, we discuss why author demographics are important in the study of hate speech: the profiles of prototypical “haters” can be used for hate speech detection, for sensibilization on and for counter-initiatives to the spread of (online) hatred.

KW - age

KW - demographics

KW - gender

KW - hate speech

KW - language area

UR - http://www.scopus.com/inward/record.url?scp=85161085725&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85161085725&partnerID=8YFLogxK

UR - https://hdl.handle.net/10067/1964940151162165141

U2 - 10.3389/frai.2023.986890

DO - 10.3389/frai.2023.986890

M3 - Article

SN - 2624-8212

VL - 6

SP - 1

EP - 12

JO - Frontiers in Artificial Intelligence

JF - Frontiers in Artificial Intelligence

M1 - 986890

ER -

Who are the haters? A corpus-based demographic analysis of authors of hate speech

Abstract

Bibliographical note

Funding

Keywords

UN SDGs

Access to Document

Persistent URL (handle)

Other files and links

Fingerprint

Cite this