Recommendations using linked data

  • Authors:
  • Rouzbeh Meymandpour;Joseph G. Davis

  • Affiliations:
  • The University of Sydney, Sydney, Australia;The University of Sydney, Sydney, Australia

  • Venue:
  • Proceedings of the 5th Ph.D. workshop on Information and knowledge
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Linked Data offers new opportunities for Semantic Web-based application development by connecting structured information from various domains. These technologies allow machines and software agents to automatically interpret and consume Linked Data and provide users with intelligent query answering services. In order to enable advanced and innovative semantic applications of Linked Data such as recommendation, social network analysis, and information clustering, a fundamental requirement is systematic metrics that allow comparison between resources. In this research, we develop a hybrid similarity metric based on the characteristics of Linked Data. In particular, we develop and demonstrate metrics for providing recommendations of closely related resources. The results of our preliminary experiments and future directions are also presented.