Improving Recommendations in Tag-based Systems with Spectral Clustering of Tag Neighbors

Rong Pan, Guandong Xu, Peter Dolog

Research output: Contribution to book/anthology/report/conference proceedingBook chapterResearchpeer-review

8 Citations (Scopus)


Tag as a useful metadata reflects the collaborative and conceptual features of documents in social collaborative annotation systems. In this paper, we propose a collaborative approach for expanding tag neighbors and investigate the spectral clustering algorithm to filter out noisy tag neighbors in order to get appropriate recommendation for users. The preliminary experiments have been conducted on MovieLens dataset to compare our proposed approach with the traditional collaborative filtering recommendation approach and naive tag neighbors expansion approach in terms of precision, and the result demonstrates that our approach could considerably improve the performance of recommendations.
Original languageEnglish
Title of host publicationComputer Science and Convergence : CSA 2011 & WCC 2011 Proceedings
EditorsJames J. Park, Han-Chieh Chao, Mohammad S. Obaidat, Jongsung Kim
Number of pages10
Publication date2012
ISBN (Print)978-94-007-2791-5
ISBN (Electronic)978-94-007-2792-2
Publication statusPublished - 2012
SeriesLecture Notes in Electrical Engineering


  • Tag Neighbors
  • Recommender System
  • Spectral Clustering
  • social tagging


Dive into the research topics of 'Improving Recommendations in Tag-based Systems with Spectral Clustering of Tag Neighbors'. Together they form a unique fingerprint.

Cite this