Détection de liens d'identité erronés en utilisant la détection de communautés dans les graphes d'identité

Joe Raad, Wouter Beek, Nathalie Pernelle, Fatiha Saïs, Frank Van Harmelen

Research output: Contribution to JournalReview articleAcademicpeer-review

Abstract

Different studies have observed that the semantic web identity predicate owl:SameAs is sometimes used incorrectly. In this paper, we show how network metrics such as the community structure of the owl:SameAs graph can be used in order to detect such possibly erroneous statements. One benefit of the here presented approach is that it can be applied to the network of owl:SameAs links, and does not rely on any additional knowledge. We evaluate our approach on 558M owl:SameAs statements scraped from the LOD cloud. This evaluation shows the ability of our approach to scale, and its efficiency in detecting erroneous identity links.

LanguageFrench
Pages95-118
Number of pages24
JournalIngenierie des Systemes d'Information
Volume23
Issue number3-4
DOIs
Publication statusPublished - Jul 2018

Keywords

  • Communities
  • Identity
  • Owl:sameAs
  • Web of data

Cite this

@article{1215a04654c84d92b809131dabdcf0f4,
title = "D{\'e}tection de liens d'identit{\'e} erron{\'e}s en utilisant la d{\'e}tection de communaut{\'e}s dans les graphes d'identit{\'e}",
abstract = "Different studies have observed that the semantic web identity predicate owl:SameAs is sometimes used incorrectly. In this paper, we show how network metrics such as the community structure of the owl:SameAs graph can be used in order to detect such possibly erroneous statements. One benefit of the here presented approach is that it can be applied to the network of owl:SameAs links, and does not rely on any additional knowledge. We evaluate our approach on 558M owl:SameAs statements scraped from the LOD cloud. This evaluation shows the ability of our approach to scale, and its efficiency in detecting erroneous identity links.",
keywords = "Communities, Identity, Owl:sameAs, Web of data",
author = "Joe Raad and Wouter Beek and Nathalie Pernelle and Fatiha Sa{\"i}s and {Van Harmelen}, Frank",
year = "2018",
month = "7",
doi = "10.3166/ISI.23.3-4.95-118",
language = "French",
volume = "23",
pages = "95--118",
journal = "Ingenierie des Systemes d'Information",
issn = "1633-1311",
publisher = "Lavoisier",
number = "3-4",

}

Détection de liens d'identité erronés en utilisant la détection de communautés dans les graphes d'identité. / Raad, Joe; Beek, Wouter; Pernelle, Nathalie; Saïs, Fatiha; Van Harmelen, Frank.

In: Ingenierie des Systemes d'Information, Vol. 23, No. 3-4, 07.2018, p. 95-118.

Research output: Contribution to JournalReview articleAcademicpeer-review

TY - JOUR

T1 - Détection de liens d'identité erronés en utilisant la détection de communautés dans les graphes d'identité

AU - Raad, Joe

AU - Beek, Wouter

AU - Pernelle, Nathalie

AU - Saïs, Fatiha

AU - Van Harmelen, Frank

PY - 2018/7

Y1 - 2018/7

N2 - Different studies have observed that the semantic web identity predicate owl:SameAs is sometimes used incorrectly. In this paper, we show how network metrics such as the community structure of the owl:SameAs graph can be used in order to detect such possibly erroneous statements. One benefit of the here presented approach is that it can be applied to the network of owl:SameAs links, and does not rely on any additional knowledge. We evaluate our approach on 558M owl:SameAs statements scraped from the LOD cloud. This evaluation shows the ability of our approach to scale, and its efficiency in detecting erroneous identity links.

AB - Different studies have observed that the semantic web identity predicate owl:SameAs is sometimes used incorrectly. In this paper, we show how network metrics such as the community structure of the owl:SameAs graph can be used in order to detect such possibly erroneous statements. One benefit of the here presented approach is that it can be applied to the network of owl:SameAs links, and does not rely on any additional knowledge. We evaluate our approach on 558M owl:SameAs statements scraped from the LOD cloud. This evaluation shows the ability of our approach to scale, and its efficiency in detecting erroneous identity links.

KW - Communities

KW - Identity

KW - Owl:sameAs

KW - Web of data

UR - http://www.scopus.com/inward/record.url?scp=85059896960&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059896960&partnerID=8YFLogxK

UR - https://isi.revuesonline.com/accueil.jsp

U2 - 10.3166/ISI.23.3-4.95-118

DO - 10.3166/ISI.23.3-4.95-118

M3 - Review article

VL - 23

SP - 95

EP - 118

JO - Ingenierie des Systemes d'Information

T2 - Ingenierie des Systemes d'Information

JF - Ingenierie des Systemes d'Information

SN - 1633-1311

IS - 3-4

ER -