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

4 Citations (Scopus)

Abstract

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
PublisherSpringer
Publication date2012
Pages355-364
ISBN (Print)978-94-007-2791-5
ISBN (Electronic)978-94-007-2792-2
DOIs
Publication statusPublished - 2012
SeriesLecture Notes in Electrical Engineering
Volume114
ISSN1876-1100

Fingerprint

Collaborative filtering
Metadata
Clustering algorithms
Experiments

Keywords

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

Cite this

Pan, R., Xu, G., & Dolog, P. (2012). Improving Recommendations in Tag-based Systems with Spectral Clustering of Tag Neighbors. In J. J. Park, H-C. Chao, M. S. Obaidat, & J. Kim (Eds.), Computer Science and Convergence: CSA 2011 & WCC 2011 Proceedings (pp. 355-364). Springer. Lecture Notes in Electrical Engineering, Vol.. 114 https://doi.org/10.1007/978-94-007-2792-2_34
Pan, Rong ; Xu, Guandong ; Dolog, Peter. / Improving Recommendations in Tag-based Systems with Spectral Clustering of Tag Neighbors. Computer Science and Convergence: CSA 2011 & WCC 2011 Proceedings. editor / James J. Park ; Han-Chieh Chao ; Mohammad S. Obaidat ; Jongsung Kim. Springer, 2012. pp. 355-364 (Lecture Notes in Electrical Engineering, Vol. 114).
@inbook{7c244fd9bf7f473a8b46898a6630086e,
title = "Improving Recommendations in Tag-based Systems with Spectral Clustering of Tag Neighbors",
abstract = "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.",
keywords = "Tag Neighbors, Recommender System, Spectral Clustering, social tagging",
author = "Rong Pan and Guandong Xu and Peter Dolog",
year = "2012",
doi = "10.1007/978-94-007-2792-2_34",
language = "English",
isbn = "978-94-007-2791-5",
series = "Lecture Notes in Electrical Engineering",
publisher = "Springer",
pages = "355--364",
editor = "Park, {James J.} and Han-Chieh Chao and Obaidat, {Mohammad S.} and Jongsung Kim",
booktitle = "Computer Science and Convergence",
address = "Germany",

}

Pan, R, Xu, G & Dolog, P 2012, Improving Recommendations in Tag-based Systems with Spectral Clustering of Tag Neighbors. in JJ Park, H-C Chao, MS Obaidat & J Kim (eds), Computer Science and Convergence: CSA 2011 & WCC 2011 Proceedings. Springer, Lecture Notes in Electrical Engineering, vol. 114, pp. 355-364. https://doi.org/10.1007/978-94-007-2792-2_34

Improving Recommendations in Tag-based Systems with Spectral Clustering of Tag Neighbors. / Pan, Rong; Xu, Guandong; Dolog, Peter.

Computer Science and Convergence: CSA 2011 & WCC 2011 Proceedings. ed. / James J. Park; Han-Chieh Chao; Mohammad S. Obaidat; Jongsung Kim. Springer, 2012. p. 355-364 (Lecture Notes in Electrical Engineering, Vol. 114).

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

TY - CHAP

T1 - Improving Recommendations in Tag-based Systems with Spectral Clustering of Tag Neighbors

AU - Pan, Rong

AU - Xu, Guandong

AU - Dolog, Peter

PY - 2012

Y1 - 2012

N2 - 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.

AB - 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.

KW - Tag Neighbors

KW - Recommender System

KW - Spectral Clustering

KW - social tagging

UR - http://www.scopus.com/inward/record.url?scp=84255199148&partnerID=8YFLogxK

U2 - 10.1007/978-94-007-2792-2_34

DO - 10.1007/978-94-007-2792-2_34

M3 - Book chapter

SN - 978-94-007-2791-5

T3 - Lecture Notes in Electrical Engineering

SP - 355

EP - 364

BT - Computer Science and Convergence

A2 - Park, James J.

A2 - Chao, Han-Chieh

A2 - Obaidat, Mohammad S.

A2 - Kim, Jongsung

PB - Springer

ER -

Pan R, Xu G, Dolog P. Improving Recommendations in Tag-based Systems with Spectral Clustering of Tag Neighbors. In Park JJ, Chao H-C, Obaidat MS, Kim J, editors, Computer Science and Convergence: CSA 2011 & WCC 2011 Proceedings. Springer. 2012. p. 355-364. (Lecture Notes in Electrical Engineering, Vol. 114). https://doi.org/10.1007/978-94-007-2792-2_34