A random walk model for item recommendation in social tagging systems

Zhu Zhang, Dajun Zeng, Ahmed Abbasi, Jing Peng, Xiaolong Zheng

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

Social tagging, as a novel approach to information organization and discovery, has been widely adopted in many Web 2.0 applications. Tags contributed by users to annotate a variety of Web resources or items provide a new type of information that can be exploited by recommender systems. Nevertheless, the sparsity of the ternary interaction data among users, items, and tags limits the performance of tag-based recommendation algorithms. In this article, we propose to deal with the sparsity problem in social tagging by applying random walks on ternary interaction graphs to explore transitive associations between users and items. The transitive associations in this article refer to the path of the link between any two nodes whose length is greater than one. Taking advantage of these transitive associations can allow more accurate measurement of the relevance between two entities (e.g., user-item, user-user, and item-item). A PageRank-like algorithm has been developed to explore these transitive associations by spreading users' preferences on an item similarity graph and spreading items' influences on a user similarity graph. Empirical evaluation on three real-world datasets demonstrates that our approach can effectively alleviate the sparsity problem and improve the quality of item recommendation.

Original languageEnglish (US)
Article number8
JournalACM Transactions on Management Information Systems
Volume4
Issue number2
DOIs
StatePublished - 2013

Fingerprint

Recommender systems
Random walk model
Social tagging
Graph
Tag
Interaction

Keywords

  • Random walk
  • Recommender systems
  • Social tagging
  • Sparsity

ASJC Scopus subject areas

  • Computer Science(all)
  • Management Information Systems

Cite this

A random walk model for item recommendation in social tagging systems. / Zhang, Zhu; Zeng, Dajun; Abbasi, Ahmed; Peng, Jing; Zheng, Xiaolong.

In: ACM Transactions on Management Information Systems, Vol. 4, No. 2, 8, 2013.

Research output: Contribution to journalArticle

Zhang, Zhu ; Zeng, Dajun ; Abbasi, Ahmed ; Peng, Jing ; Zheng, Xiaolong. / A random walk model for item recommendation in social tagging systems. In: ACM Transactions on Management Information Systems. 2013 ; Vol. 4, No. 2.
@article{70c7da530c2444c29528098b2b9180b4,
title = "A random walk model for item recommendation in social tagging systems",
abstract = "Social tagging, as a novel approach to information organization and discovery, has been widely adopted in many Web 2.0 applications. Tags contributed by users to annotate a variety of Web resources or items provide a new type of information that can be exploited by recommender systems. Nevertheless, the sparsity of the ternary interaction data among users, items, and tags limits the performance of tag-based recommendation algorithms. In this article, we propose to deal with the sparsity problem in social tagging by applying random walks on ternary interaction graphs to explore transitive associations between users and items. The transitive associations in this article refer to the path of the link between any two nodes whose length is greater than one. Taking advantage of these transitive associations can allow more accurate measurement of the relevance between two entities (e.g., user-item, user-user, and item-item). A PageRank-like algorithm has been developed to explore these transitive associations by spreading users' preferences on an item similarity graph and spreading items' influences on a user similarity graph. Empirical evaluation on three real-world datasets demonstrates that our approach can effectively alleviate the sparsity problem and improve the quality of item recommendation.",
keywords = "Random walk, Recommender systems, Social tagging, Sparsity",
author = "Zhu Zhang and Dajun Zeng and Ahmed Abbasi and Jing Peng and Xiaolong Zheng",
year = "2013",
doi = "10.1145/2490860",
language = "English (US)",
volume = "4",
journal = "ACM Transactions on Management Information Systems",
issn = "2158-656X",
publisher = "Association for Computing Machinery (ACM)",
number = "2",

}

TY - JOUR

T1 - A random walk model for item recommendation in social tagging systems

AU - Zhang, Zhu

AU - Zeng, Dajun

AU - Abbasi, Ahmed

AU - Peng, Jing

AU - Zheng, Xiaolong

PY - 2013

Y1 - 2013

N2 - Social tagging, as a novel approach to information organization and discovery, has been widely adopted in many Web 2.0 applications. Tags contributed by users to annotate a variety of Web resources or items provide a new type of information that can be exploited by recommender systems. Nevertheless, the sparsity of the ternary interaction data among users, items, and tags limits the performance of tag-based recommendation algorithms. In this article, we propose to deal with the sparsity problem in social tagging by applying random walks on ternary interaction graphs to explore transitive associations between users and items. The transitive associations in this article refer to the path of the link between any two nodes whose length is greater than one. Taking advantage of these transitive associations can allow more accurate measurement of the relevance between two entities (e.g., user-item, user-user, and item-item). A PageRank-like algorithm has been developed to explore these transitive associations by spreading users' preferences on an item similarity graph and spreading items' influences on a user similarity graph. Empirical evaluation on three real-world datasets demonstrates that our approach can effectively alleviate the sparsity problem and improve the quality of item recommendation.

AB - Social tagging, as a novel approach to information organization and discovery, has been widely adopted in many Web 2.0 applications. Tags contributed by users to annotate a variety of Web resources or items provide a new type of information that can be exploited by recommender systems. Nevertheless, the sparsity of the ternary interaction data among users, items, and tags limits the performance of tag-based recommendation algorithms. In this article, we propose to deal with the sparsity problem in social tagging by applying random walks on ternary interaction graphs to explore transitive associations between users and items. The transitive associations in this article refer to the path of the link between any two nodes whose length is greater than one. Taking advantage of these transitive associations can allow more accurate measurement of the relevance between two entities (e.g., user-item, user-user, and item-item). A PageRank-like algorithm has been developed to explore these transitive associations by spreading users' preferences on an item similarity graph and spreading items' influences on a user similarity graph. Empirical evaluation on three real-world datasets demonstrates that our approach can effectively alleviate the sparsity problem and improve the quality of item recommendation.

KW - Random walk

KW - Recommender systems

KW - Social tagging

KW - Sparsity

UR - http://www.scopus.com/inward/record.url?scp=84885626865&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84885626865&partnerID=8YFLogxK

U2 - 10.1145/2490860

DO - 10.1145/2490860

M3 - Article

VL - 4

JO - ACM Transactions on Management Information Systems

JF - ACM Transactions on Management Information Systems

SN - 2158-656X

IS - 2

M1 - 8

ER -