Monitoring semantic relatedness and revealing fairness and biases through trend tests

An emerging application domain concerning content-based recommender systems provides a better consideration of the semantics behind textual descriptions. Traditional approaches often miss relevant information due to their sole focus on syntax. However, the Semantic Web community has enriched resourc...

Full description

Saved in:
Bibliographic Details
Main Authors: Jean-Rémi Bourguet, Adama Sow
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:International Journal of Information Management Data Insights
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2667096824000946
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846150123775590400
author Jean-Rémi Bourguet
Adama Sow
author_facet Jean-Rémi Bourguet
Adama Sow
author_sort Jean-Rémi Bourguet
collection DOAJ
description An emerging application domain concerning content-based recommender systems provides a better consideration of the semantics behind textual descriptions. Traditional approaches often miss relevant information due to their sole focus on syntax. However, the Semantic Web community has enriched resources with cultural and linguistic background knowledge, offering new standards for word categorization. This paper proposes a framework that combines the information extractor ReVerb with the WordNet taxonomy to monitor global semantic relatedness scores. Additionally, an experimental validation confronts human-based semantic relatedness scores with theoretical ones, employing Mann–Kendall trend tests to reveal fairness and biases. Overall, our framework introduces a novel approach to semantic relatedness monitoring by providing valuable insights into fairness and biases.
format Article
id doaj-art-b3bc1cad9ee34f93b997537db3f56876
institution Kabale University
issn 2667-0968
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series International Journal of Information Management Data Insights
spelling doaj-art-b3bc1cad9ee34f93b997537db3f568762024-11-29T06:25:23ZengElsevierInternational Journal of Information Management Data Insights2667-09682025-06-0151100305Monitoring semantic relatedness and revealing fairness and biases through trend testsJean-Rémi Bourguet0Adama Sow1Departmento de Ciência da Computação, Universidade Vila Velha (UVV), Avenida Comissário José Dantas de Melo, 21 - Boa Vista II, CEP 29102-920 Vila Velha, Brazil; Dipartimento di Scienze Politiche, Scienze della Comunicazione ed Ingegneria dell’Informazione, Università degli Studi di Sassari (UNISS), Viale Mancini 5 07100 Sassari, Italy; Corresponding author at: Departmento de Ciência da Computação, Universidade Vila Velha (UVV), Avenida Comissário José Dantas de Melo, 21 - Boa Vista II, CEP 29102-920 Vila Velha, Brazil.Département Génie Informatique et Télécommunications, Ecole Polytechnique de Thiès (EPT), Route Base aérienne Diakhao BP 64551 Dakar-Fann, Senegal; Department of Computer Science and Software Engineering, Université de Laval 1065 avenue de la Médecine, G1K 7P4 Quebec, CanadaAn emerging application domain concerning content-based recommender systems provides a better consideration of the semantics behind textual descriptions. Traditional approaches often miss relevant information due to their sole focus on syntax. However, the Semantic Web community has enriched resources with cultural and linguistic background knowledge, offering new standards for word categorization. This paper proposes a framework that combines the information extractor ReVerb with the WordNet taxonomy to monitor global semantic relatedness scores. Additionally, an experimental validation confronts human-based semantic relatedness scores with theoretical ones, employing Mann–Kendall trend tests to reveal fairness and biases. Overall, our framework introduces a novel approach to semantic relatedness monitoring by providing valuable insights into fairness and biases.http://www.sciencedirect.com/science/article/pii/S2667096824000946Semantic relatednessFairnessBiasesWordNetReVerbVisualization
spellingShingle Jean-Rémi Bourguet
Adama Sow
Monitoring semantic relatedness and revealing fairness and biases through trend tests
International Journal of Information Management Data Insights
Semantic relatedness
Fairness
Biases
WordNet
ReVerb
Visualization
title Monitoring semantic relatedness and revealing fairness and biases through trend tests
title_full Monitoring semantic relatedness and revealing fairness and biases through trend tests
title_fullStr Monitoring semantic relatedness and revealing fairness and biases through trend tests
title_full_unstemmed Monitoring semantic relatedness and revealing fairness and biases through trend tests
title_short Monitoring semantic relatedness and revealing fairness and biases through trend tests
title_sort monitoring semantic relatedness and revealing fairness and biases through trend tests
topic Semantic relatedness
Fairness
Biases
WordNet
ReVerb
Visualization
url http://www.sciencedirect.com/science/article/pii/S2667096824000946
work_keys_str_mv AT jeanremibourguet monitoringsemanticrelatednessandrevealingfairnessandbiasesthroughtrendtests
AT adamasow monitoringsemanticrelatednessandrevealingfairnessandbiasesthroughtrendtests