A trust-enriched approach for item-based collaborative filtering recommendations

Haiyang Zhang, Ivan Ganchev, Nikola S. Nikolov, Mairtin O'droma

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The item-based collaborative filtering (CF) is one of the most successful approaches utilized by the recommendation systems. The basic concept behind it is to recommend those items to users which are similar to other items that these users have been interested in recently. This paper proposes a hybrid method that integrates user trust relations with item-based CF. This is achieved by incorporating user social similarities into the computation of item similarities. Performance evaluation of the proposed method is done by comparing the results with the traditional item-based CF. The experiment results demonstrate that the proposed approach achieves better accuracy.

Original languageEnglish
Title of host publicationProceedings - 2016 IEEE 12th International Conference on Intelligent Computer Communication and Processing, ICCP 2016
EditorsRodica Potolea, Radu Razvan Slavescu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages65-68
Number of pages4
ISBN (Electronic)9781509038992
DOIs
Publication statusPublished - 7 Nov 2016
Event12th IEEE International Conference on Intelligent Computer Communication and Processing, ICCP 2016 - Cluj-Napoca, Romania
Duration: 8 Sep 201610 Sep 2016

Publication series

NameProceedings - 2016 IEEE 12th International Conference on Intelligent Computer Communication and Processing, ICCP 2016

Conference

Conference12th IEEE International Conference on Intelligent Computer Communication and Processing, ICCP 2016
Country/TerritoryRomania
CityCluj-Napoca
Period8/09/1610/09/16

Keywords

  • Collaborative filtering
  • Item recommendations
  • Item-based filtering
  • Social relations

Fingerprint

Dive into the research topics of 'A trust-enriched approach for item-based collaborative filtering recommendations'. Together they form a unique fingerprint.

Cite this