Cross social networks interests predictions based on graph features

Amit Tiroshi, Shlomo Berkovsky, Mohamed Ali Kaafar, Terence Chen, Tsvi Kuflik

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contribution

21 Citations (Scopus)

Abstract

The tremendous popularity of Online Social Networks (OSN) has led to situations, where users have their profiles spread across multiple networks. These partial profiles reflect different user characteristics, depending mainly on the nature of the network, e.g., Facebook's social vs. LinkedIn's professional focus. Combining data gathered by multiple networks may benefit individual users, and the community as a whole, as this could facilitate the provision of more accurate services and recommendations. This paper reports on an exploratory study of the process of making such recommendations using a unique multi-network dataset containing user interests across multiple domains, e.g., music, books, and movies. We represent the data using a graph model and generate recommendations using a set of features extracted from and populated by the model. We assess the contribution of various network-and domain-related features to the accuracy of the recommendations and motivate future work into automated feature selection.

Original languageEnglish
Title of host publicationProceedings of the 7th ACM conference on Recommender systems, RecSys '13
Place of PublicationNew York
PublisherAssociation for Computing Machinery (ACM)
Pages319-322
Number of pages4
ISBN (Electronic)9781450324090
ISBN (Print)9781450324090
DOIs
Publication statusPublished - 2013
Externally publishedYes
Event7th ACM Conference on Recommender Systems, RecSys 2013 - Hong Kong, China
Duration: 12 Oct 201316 Oct 2013

Conference

Conference7th ACM Conference on Recommender Systems, RecSys 2013
CountryChina
CityHong Kong
Period12/10/1316/10/13

Keywords

  • graph model
  • interests prediction
  • social networks

Fingerprint Dive into the research topics of 'Cross social networks interests predictions based on graph features'. Together they form a unique fingerprint.

Cite this