Skip to main content

2014 | OriginalPaper | Buchkapitel

Popular Books and Linked Data: Some Results for the ESWC’14 RecSys Challenge

verfasst von : Michael Schuhmacher, Christian Meilicke

Erschienen in: Semantic Web Evaluation Challenge

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Within this paper we present our contribution to Task 2 of the ESWC’14 Recommender Systems Challenge. First we describe an unpersonalized baseline approach that uses no linked-data but applies a naive way to compute the overall popularity of the items observed in the training data. Despite being very simple and unpersonalized, we achieve a competitive \(F_1\) measure of 0.5583. Then we describe an algorithm that makes use of several features acquired from DBpedia, like author and type, and self-generated features like abstract-based keywords, for item representation and comparison. Item recommendations are generated by a mixture-model of individual classifiers that have been learned per feature on a user neighborhood cluster in combination with a global classifier learned on all training data. While our Linked-Data-based approach achieves an \(\mathrm{F}_1\) measure of 0.5649, the increase over the popularity baseline remains surprisingly low.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Fußnoten
2
As we discovered an implementation bug in the original LDR system as used for the ESWC Challenge, we present here the fixed system which takes a slightly different approach to feature representation and classifier learning.
 
3
The challenge data contain some inconsistencies, as e.g. different items have the same DBpedia URI (384 duplicates), or the same title (319 duplicates). We opt explicitly to not fix those errors and work with the dataset as given.
 
4
We abbreviate namespaces according to common rules (http://​www.​prefix.​cc).
 
5
For experiments we used the Weka 3.7.10 Java API with LibSVM 1.0.5, alternatingDecisionTrees 1.0.5, and bestFirstTree 1.0.3.
 
6
The original challenge submission (name UniMannheim) achieved an \(F_1\) of 0.5607 with a Naive Bayes classifier and an one model approach, however, we discovered later that our competition system contained a coding bug in the classifier learning. We thus present here the post-challenge evaluation for the fixed system, which uses a slightly different classifier configuration.
 
Literatur
1.
Zurück zum Zitat Beygelzimer, A., Kakade, S., Langford, J.: Cover trees for nearest neighbor. In: ICML’06: Proceedings of the 23rd International Conference on Machine Learning, pp. 97–104. ACM Press, New York (2006) Beygelzimer, A., Kakade, S., Langford, J.: Cover trees for nearest neighbor. In: ICML’06: Proceedings of the 23rd International Conference on Machine Learning, pp. 97–104. ACM Press, New York (2006)
2.
Zurück zum Zitat Herlocker, J., Konstan, J., Riedl, J.: An empirical analysis of design choices in neighborhood-based collaborative filtering algorithms. Inf. Retr. 5(4), 287–310 (2002)CrossRef Herlocker, J., Konstan, J., Riedl, J.: An empirical analysis of design choices in neighborhood-based collaborative filtering algorithms. Inf. Retr. 5(4), 287–310 (2002)CrossRef
3.
Zurück zum Zitat Jannach, D., Zanker, M., Felfernig, A., Friedrich, G.: Recommender Systems: An Introduction. Cambridge University Press, Cambridge (2011) Jannach, D., Zanker, M., Felfernig, A., Friedrich, G.: Recommender Systems: An Introduction. Cambridge University Press, Cambridge (2011)
Metadaten
Titel
Popular Books and Linked Data: Some Results for the ESWC’14 RecSys Challenge
verfasst von
Michael Schuhmacher
Christian Meilicke
Copyright-Jahr
2014
DOI
https://doi.org/10.1007/978-3-319-12024-9_23

Neuer Inhalt