Exploring the Plausibility of Hate and Counter Speech Detectors with Explainable AI Article Swipe

PDF

Adrian Jaques Böck , Djordje Slijepčević , Matthias Zeppelzauer ·

YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2407.20274

In this paper we investigate the explainability of transformer models and their plausibility for hate speech and counter speech detection. We compare representatives of four different explainability approaches, i.e., gradient-based, perturbation-based, attention-based, and prototype-based approaches, and analyze them quantitatively with an ablation study and qualitatively in a user study. Results show that perturbation-based explainability performs best, followed by gradient-based and attention-based explainability. Prototypebased experiments did not yield useful results. Overall, we observe that explainability strongly supports the users in better understanding the model predictions.

Related Topics

Computer Science

Philosophy

Concepts

Detector Linguistics Psychology Computer science Speech recognition Natural language processing Philosophy Telecommunications

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2407.20274
PDF: https://arxiv.org/pdf/2407.20274
OA Status: green
Related Works: 10
OpenAlex ID: https://openalex.org/W4401202655

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4401202655

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2407.20274

Digital Object Identifier
Title: Exploring the Plausibility of Hate and Counter Speech Detectors with Explainable AI

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2024

Year of publication
Publication date: 2024-07-25

Full publication date if available
Authors: Adrian Jaques Böck, Djordje Slijepčević, Matthias Zeppelzauer

List of authors in order
Landing page: https://arxiv.org/abs/2407.20274

Publisher landing page
PDF URL: https://arxiv.org/pdf/2407.20274

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2407.20274

Direct OA link when available
Concepts: Detector, Linguistics, Psychology, Computer science, Speech recognition, Natural language processing, Philosophy, Telecommunications

Top concepts (fields/topics) attached by OpenAlex
Cited by: 0

Total citation count in OpenAlex
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4401202655
doi	https://doi.org/10.48550/arxiv.2407.20274
ids.doi	https://doi.org/10.48550/arxiv.2407.20274
ids.openalex	https://openalex.org/W4401202655
fwci
type	preprint
title	Exploring the Plausibility of Hate and Counter Speech Detectors with Explainable AI
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T11689
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9825999736785889
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1702
topics[0].subfield.display_name	Artificial Intelligence
topics[0].display_name	Adversarial Robustness in Machine Learning
topics[1].id	https://openalex.org/T12262
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9800000190734863
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1702
topics[1].subfield.display_name	Artificial Intelligence
topics[1].display_name	Hate Speech and Cyberbullying Detection
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C94915269
concepts[0].level	2
concepts[0].score	0.6116741895675659
concepts[0].wikidata	https://www.wikidata.org/wiki/Q1834857
concepts[0].display_name	Detector
concepts[1].id	https://openalex.org/C41895202
concepts[1].level	1
concepts[1].score	0.401358962059021
concepts[1].wikidata	https://www.wikidata.org/wiki/Q8162
concepts[1].display_name	Linguistics
concepts[2].id	https://openalex.org/C15744967
concepts[2].level	0
concepts[2].score	0.39310216903686523
concepts[2].wikidata	https://www.wikidata.org/wiki/Q9418
concepts[2].display_name	Psychology
concepts[3].id	https://openalex.org/C41008148
concepts[3].level	0
concepts[3].score	0.37139618396759033
concepts[3].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[3].display_name	Computer science
concepts[4].id	https://openalex.org/C28490314
concepts[4].level	1
concepts[4].score	0.3694204092025757
concepts[4].wikidata	https://www.wikidata.org/wiki/Q189436
concepts[4].display_name	Speech recognition
concepts[5].id	https://openalex.org/C204321447
concepts[5].level	1
concepts[5].score	0.3207957446575165
concepts[5].wikidata	https://www.wikidata.org/wiki/Q30642
concepts[5].display_name	Natural language processing
concepts[6].id	https://openalex.org/C138885662
concepts[6].level	0
concepts[6].score	0.21885812282562256
concepts[6].wikidata	https://www.wikidata.org/wiki/Q5891
concepts[6].display_name	Philosophy
concepts[7].id	https://openalex.org/C76155785
concepts[7].level	1
concepts[7].score	0.10776135325431824
concepts[7].wikidata	https://www.wikidata.org/wiki/Q418
concepts[7].display_name	Telecommunications
keywords[0].id	https://openalex.org/keywords/detector
keywords[0].score	0.6116741895675659
keywords[0].display_name	Detector
keywords[1].id	https://openalex.org/keywords/linguistics
keywords[1].score	0.401358962059021
keywords[1].display_name	Linguistics
keywords[2].id	https://openalex.org/keywords/psychology
keywords[2].score	0.39310216903686523
keywords[2].display_name	Psychology
keywords[3].id	https://openalex.org/keywords/computer-science
keywords[3].score	0.37139618396759033
keywords[3].display_name	Computer science
keywords[4].id	https://openalex.org/keywords/speech-recognition
keywords[4].score	0.3694204092025757
keywords[4].display_name	Speech recognition
keywords[5].id	https://openalex.org/keywords/natural-language-processing
keywords[5].score	0.3207957446575165
keywords[5].display_name	Natural language processing
keywords[6].id	https://openalex.org/keywords/philosophy
keywords[6].score	0.21885812282562256
keywords[6].display_name	Philosophy
keywords[7].id	https://openalex.org/keywords/telecommunications
keywords[7].score	0.10776135325431824
keywords[7].display_name	Telecommunications
language	en
locations[0].id	pmh:oai:arXiv.org:2407.20274
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license	cc-by
locations[0].pdf_url	https://arxiv.org/pdf/2407.20274
locations[0].version	submittedVersion
locations[0].raw_type
locations[0].license_id	https://openalex.org/licenses/cc-by
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2407.20274
locations[1].id	doi:10.48550/arxiv.2407.20274
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license	cc-by
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id	https://openalex.org/licenses/cc-by
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2407.20274
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5109570079
authorships[0].author.orcid	https://orcid.org/0000-0003-1972-0473
authorships[0].author.display_name	Adrian Jaques Böck
authorships[0].author_position	first
authorships[0].raw_author_name	Böck, Adrian Jaques
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5055814440
authorships[1].author.orcid	https://orcid.org/0000-0002-2295-7466
authorships[1].author.display_name	Djordje Slijepčević
authorships[1].author_position	middle
authorships[1].raw_author_name	Slijepčević, Djordje
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5060926433
authorships[2].author.orcid	https://orcid.org/0000-0003-0413-4746
authorships[2].author.display_name	Matthias Zeppelzauer
authorships[2].author_position	last
authorships[2].raw_author_name	Zeppelzauer, Matthias
authorships[2].is_corresponding	False
has_content.pdf	True
has_content.grobid_xml	True
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2407.20274
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2024-08-01T00:00:00
display_name	Exploring the Plausibility of Hate and Counter Speech Detectors with Explainable AI
has_fulltext	True
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T11689
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9825999736785889
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1702
primary_topic.subfield.display_name	Artificial Intelligence
primary_topic.display_name	Adversarial Robustness in Machine Learning
related_works	https://openalex.org/W4391375266, https://openalex.org/W2748952813, https://openalex.org/W2366906938, https://openalex.org/W2349391998, https://openalex.org/W4205655149, https://openalex.org/W2000775715, https://openalex.org/W2931662336, https://openalex.org/W2795393339, https://openalex.org/W2626393719, https://openalex.org/W4390618967
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2407.20274
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license	cc-by
best_oa_location.pdf_url	https://arxiv.org/pdf/2407.20274
best_oa_location.version	submittedVersion
best_oa_location.raw_type
best_oa_location.license_id	https://openalex.org/licenses/cc-by
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2407.20274
primary_location.id	pmh:oai:arXiv.org:2407.20274
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license	cc-by
primary_location.pdf_url	https://arxiv.org/pdf/2407.20274
primary_location.version	submittedVersion
primary_location.raw_type
primary_location.license_id	https://openalex.org/licenses/cc-by
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2407.20274
publication_date	2024-07-25
publication_year	2024
referenced_works_count	0
abstract_inverted_index.a	46
abstract_inverted_index.In	0
abstract_inverted_index.We	20
abstract_inverted_index.an	40
abstract_inverted_index.by	57
abstract_inverted_index.in	45, 78
abstract_inverted_index.of	7, 23
abstract_inverted_index.we	3, 70
abstract_inverted_index.and	10, 16, 32, 35, 43, 59
abstract_inverted_index.did	64
abstract_inverted_index.for	13
abstract_inverted_index.not	65
abstract_inverted_index.the	5, 76, 81
abstract_inverted_index.four	24
abstract_inverted_index.hate	14
abstract_inverted_index.show	50
abstract_inverted_index.that	51, 72
abstract_inverted_index.them	37
abstract_inverted_index.this	1
abstract_inverted_index.user	47
abstract_inverted_index.with	39
abstract_inverted_index.best,	55
abstract_inverted_index.i.e.,	28
abstract_inverted_index.model	82
abstract_inverted_index.paper	2
abstract_inverted_index.study	42
abstract_inverted_index.their	11
abstract_inverted_index.users	77
abstract_inverted_index.yield	66
abstract_inverted_index.better	79
abstract_inverted_index.models	9
abstract_inverted_index.speech	15, 18
abstract_inverted_index.study.	48
abstract_inverted_index.useful	67
abstract_inverted_index.Results	49
abstract_inverted_index.analyze	36
abstract_inverted_index.compare	21
abstract_inverted_index.counter	17
abstract_inverted_index.observe	71
abstract_inverted_index.Overall,	69
abstract_inverted_index.ablation	41
abstract_inverted_index.followed	56
abstract_inverted_index.performs	54
abstract_inverted_index.results.	68
abstract_inverted_index.strongly	74
abstract_inverted_index.supports	75
abstract_inverted_index.different	25
abstract_inverted_index.detection.	19
abstract_inverted_index.approaches,	27, 34
abstract_inverted_index.experiments	63
abstract_inverted_index.investigate	4
abstract_inverted_index.transformer	8
abstract_inverted_index.plausibility	12
abstract_inverted_index.predictions.	83
abstract_inverted_index.qualitatively	44
abstract_inverted_index.understanding	80
abstract_inverted_index.Prototypebased	62
abstract_inverted_index.explainability	6, 26, 53, 73
abstract_inverted_index.gradient-based	58
abstract_inverted_index.quantitatively	38
abstract_inverted_index.attention-based	60
abstract_inverted_index.explainability.	61
abstract_inverted_index.gradient-based,	29
abstract_inverted_index.prototype-based	33
abstract_inverted_index.representatives	22
abstract_inverted_index.attention-based,	31
abstract_inverted_index.perturbation-based	52
abstract_inverted_index.perturbation-based,	30
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	3
citation_normalized_percentile