User-centric pattern mining on knowledge graphs: An archaeological case study

W. X. Wilcke, V. de Boer, M. T.M. de Kleijn, F. A.H. van Harmelen, H. J. Scholten

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

In recent years, there has been a growing interest from the digital humanities in knowledge graphs as data modelling paradigm. Already, this has led to the creation of many such knowledge graphs, many of which are now available as part of the Linked Open Data cloud. This presents new opportunities for data mining. In this work, we develop, implement, and evaluate (both data-driven and user-driven) an end-to-end pipeline for user-centric pattern mining on knowledge graphs in the humanities. This pipeline combines constrained generalized association rule mining with natural language output and facet rule browsing to allow for transparency and interpretability—two key domain requirements. Experiments in the archaeological domain show that domain experts were positively surprised by the range of patterns that were discovered and were overall optimistic about the future potential of this approach.

Original languageEnglish
JournalJournal of Web Semantics
DOIs
Publication statusAccepted/In press - 1 Jan 2018

Fingerprint

Pipelines
Association rules
Transparency
Data mining
Data structures
Experiments

Keywords

  • Archaeology
  • Digital humanities
  • Generalized association rules
  • Knowledge graphs
  • Pattern mining
  • User-centric

Cite this

@article{8ec1e0042c73494f8a2215af67643357,
title = "User-centric pattern mining on knowledge graphs: An archaeological case study",
abstract = "In recent years, there has been a growing interest from the digital humanities in knowledge graphs as data modelling paradigm. Already, this has led to the creation of many such knowledge graphs, many of which are now available as part of the Linked Open Data cloud. This presents new opportunities for data mining. In this work, we develop, implement, and evaluate (both data-driven and user-driven) an end-to-end pipeline for user-centric pattern mining on knowledge graphs in the humanities. This pipeline combines constrained generalized association rule mining with natural language output and facet rule browsing to allow for transparency and interpretability—two key domain requirements. Experiments in the archaeological domain show that domain experts were positively surprised by the range of patterns that were discovered and were overall optimistic about the future potential of this approach.",
keywords = "Archaeology, Digital humanities, Generalized association rules, Knowledge graphs, Pattern mining, User-centric",
author = "Wilcke, {W. X.} and {de Boer}, V. and {de Kleijn}, {M. T.M.} and {van Harmelen}, {F. A.H.} and Scholten, {H. J.}",
year = "2018",
month = "1",
day = "1",
doi = "10.1016/j.websem.2018.12.004",
language = "English",
journal = "Journal of Web Semantics",
issn = "1570-8268",
publisher = "Elsevier",

}

User-centric pattern mining on knowledge graphs : An archaeological case study. / Wilcke, W. X.; de Boer, V.; de Kleijn, M. T.M.; van Harmelen, F. A.H.; Scholten, H. J.

In: Journal of Web Semantics, 01.01.2018.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - User-centric pattern mining on knowledge graphs

T2 - An archaeological case study

AU - Wilcke, W. X.

AU - de Boer, V.

AU - de Kleijn, M. T.M.

AU - van Harmelen, F. A.H.

AU - Scholten, H. J.

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In recent years, there has been a growing interest from the digital humanities in knowledge graphs as data modelling paradigm. Already, this has led to the creation of many such knowledge graphs, many of which are now available as part of the Linked Open Data cloud. This presents new opportunities for data mining. In this work, we develop, implement, and evaluate (both data-driven and user-driven) an end-to-end pipeline for user-centric pattern mining on knowledge graphs in the humanities. This pipeline combines constrained generalized association rule mining with natural language output and facet rule browsing to allow for transparency and interpretability—two key domain requirements. Experiments in the archaeological domain show that domain experts were positively surprised by the range of patterns that were discovered and were overall optimistic about the future potential of this approach.

AB - In recent years, there has been a growing interest from the digital humanities in knowledge graphs as data modelling paradigm. Already, this has led to the creation of many such knowledge graphs, many of which are now available as part of the Linked Open Data cloud. This presents new opportunities for data mining. In this work, we develop, implement, and evaluate (both data-driven and user-driven) an end-to-end pipeline for user-centric pattern mining on knowledge graphs in the humanities. This pipeline combines constrained generalized association rule mining with natural language output and facet rule browsing to allow for transparency and interpretability—two key domain requirements. Experiments in the archaeological domain show that domain experts were positively surprised by the range of patterns that were discovered and were overall optimistic about the future potential of this approach.

KW - Archaeology

KW - Digital humanities

KW - Generalized association rules

KW - Knowledge graphs

KW - Pattern mining

KW - User-centric

UR - http://www.scopus.com/inward/record.url?scp=85058640501&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058640501&partnerID=8YFLogxK

U2 - 10.1016/j.websem.2018.12.004

DO - 10.1016/j.websem.2018.12.004

M3 - Article

JO - Journal of Web Semantics

JF - Journal of Web Semantics

SN - 1570-8268

ER -