Bias in knowledge graphs - An empirical study with movie recommendation and different language editions of DBpedia


Voit, Michael Matthias ; Paulheim, Heiko


[img] PDF
OASIcs-LDK-2021-14.pdf - Published

Download (695kB)

DOI: https://doi.org/10.4230/OASIcs.LDK.2021.14
URL: https://madoc.bib.uni-mannheim.de/60239
Additional URL: https://arxiv.org/abs/2105.00674
URN: urn:nbn:de:bsz:180-madoc-602395
Document Type: Conference or workshop publication
Year of publication: 2021
Book title: 3rd Conference on Language, Data and Knowledge (LDK 2021) : September 1–3, 2021, Zaragoza, Spain
The title of a journal, publication series: Open Access Series in Informatics : OASIcs
Volume: 93, Article 14
Page range: 14:1-14:13
Conference title: Conference on Language, Data and Knowledge
Location of the conference venue: Zaragoza, Spain
Date of the conference: 01.-04.09.2021
Publisher: Gromann, Dagmar ; Sérasset, Gilles ; Declerck, Thierry ; McCra, John P. ; Gracia, Jorge ; Bosque-Gil, Julia ; Bobillo, Fernando ; Heinisch, Barbara
Place of publication: Wadern
Publishing house: Leibniz-Zentrum für Informatik
ISBN: 978-3-95977-199-3
ISSN: 2190-6807
Related URLs:
Publication language: English
Institution: School of Business Informatics and Mathematics > Web Data Mining (Paulheim 2018-)
Pre-existing license: Creative Commons Attribution 4.0 International (CC BY 4.0)
Subject: 004 Computer science, internet
Abstract: Public knowledge graphs such as DBpedia and Wikidata have been recognized as interesting sources of background knowledge to build content-based recommender systems. They can be used to add information about the items to be recommended and links between those. While quite a few approaches for exploiting knowledge graphs have been proposed, most of them aim at optimizing the recommendation strategy while using a fixed knowledge graph. In this paper, we take a different approach, i.e., we fix the recommendation strategy and observe changes when using different underlying knowledge graphs. Particularly, we use different language editions of DBpedia. We show that the usage of different knowledge graphs does not only lead to differently biased recommender systems, but also to recommender systems that differ in performance for particular fields of recommendations.

Dieser Eintrag ist Teil der Universitätsbibliographie.

Das Dokument wird vom Publikationsserver der Universitätsbibliothek Mannheim bereitgestellt.




Metadata export


Citation


+ Search Authors in

BASE: Voit, Michael Matthias ; Paulheim, Heiko

Google Scholar: Voit, Michael Matthias ; Paulheim, Heiko

ORCID: Voit, Michael Matthias ; Paulheim, Heiko ORCID: 0000-0003-4386-8195

+ Download Statistics

Downloads per month over past year

View more statistics



You have found an error? Please let us know about your desired correction here: E-Mail


Actions (login required)

Show item Show item