Supporting social recommendations with activity-balanced clustering

F. Maxwell Harper, Shilad Sen, Dan Frankowski

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

11 Scopus citations

Abstract

In support of social interaction and information sharing, online communities commonly provide interfaces for users to form or interact with groups. For example, a user of the social music recommendation site last.fm might join the "First Wave Punk" group to discuss his or her favorite band (The Clash) and listen to playlists generated by fellow fans. Clustering techniques provide the potential to automatically discover groups of users who appear to share interests. We explore this idea by describing algorithms for clustering users of an online community and automatically describing the resulting user groups. We designed these techniques for use in an online recommendation system with no pre-existing group functionality, which led us to develop an "activity-balanced clustering" algorithm that considers both user activity and user interests in forming clusters.

Original languageEnglish (US)
Title of host publicationRecSys'07
Subtitle of host publicationProceedings of the 2007 ACM Conference on Recommender Systems
Pages165-168
Number of pages4
DOIs
StatePublished - Dec 1 2007
EventRecSys'07: 2007 1st ACM Conference on Recommender Systems - Minneapolis, MN, United States
Duration: Oct 19 2007Oct 20 2007

Publication series

NameRecSys'07: Proceedings of the 2007 ACM Conference on Recommender Systems

Other

OtherRecSys'07: 2007 1st ACM Conference on Recommender Systems
CountryUnited States
CityMinneapolis, MN
Period10/19/0710/20/07

Keywords

  • Activity-balanced clustering
  • User group summarization

Fingerprint Dive into the research topics of 'Supporting social recommendations with activity-balanced clustering'. Together they form a unique fingerprint.

Cite this