Applying associative retrieval techniques to alleviate the sparsity problem in collaborative filtering

Research output: Contribution to journalArticle

443 Citations (Scopus)

Abstract

Recommender systems are being widely applied in many application settings to suggest products, services, and information items to potential consumers, Collaborative filtering, the most successful recommendation approach, makes recommendations based on past transactions and feedback from consumers sharing similar interests. A major problem limiting the usefulness of collaborative filtering is the sparsity problem, which refers to a situation in which transactional or feedback data is sparse and insufficient to identify similarities in consumer interests. In this article, we propose to deal with this sparsity problem by applying an associative retrieval framework and related spreading activation algorithms to explore transitive associations among consumers through their past transactions and feedback. Such transitive associations are a valuable source of information to help infer consumer interests and can be explored to deal with the sparsity problem. To evaluate the effectiveness of our approach, we have conducted an experimental study using a data set from an online bookstore. We experimented with three spreading activation algorithms including a constrained Leaky Capacitor algorithm, a branch-and-bound serial symbolic search algorithm, and a Hopfield net parallel relaxation search algorithm. These algorithms were compared with several collaborative filtering approaches that do not consider the transitive associations: a simple graph search approach, two variations of the user-based approach, and an item-based approach. Our experimental results indicate that spreading activation-based approaches significantly out-performed the other collaborative filtering methods as measured by recommendation precision, recall, the F-measure, and the rank score. We also observed the over-activation effect of the spreading activation approach, that is, incorporating transitive associations with past transactional data that is not sparse may "dilute" the data used to infer user preferences and lead to degradation in recommendation performance.

Original languageEnglish (US)
Pages (from-to)116-142
Number of pages27
JournalACM Transactions on Information Systems
Volume22
Issue number1
DOIs
StatePublished - Jan 2004

Fingerprint

Collaborative filtering
Chemical activation
Feedback
Recommender systems
Capacitors
Degradation
Activation

Keywords

  • Associative retrieval
  • Collaborative filtering
  • Recommender system
  • Sparsity problem
  • Spreading activation

ASJC Scopus subject areas

  • Information Systems

Cite this

@article{bfd6dd414a1341eaa0de49f96db150fa,
title = "Applying associative retrieval techniques to alleviate the sparsity problem in collaborative filtering",
abstract = "Recommender systems are being widely applied in many application settings to suggest products, services, and information items to potential consumers, Collaborative filtering, the most successful recommendation approach, makes recommendations based on past transactions and feedback from consumers sharing similar interests. A major problem limiting the usefulness of collaborative filtering is the sparsity problem, which refers to a situation in which transactional or feedback data is sparse and insufficient to identify similarities in consumer interests. In this article, we propose to deal with this sparsity problem by applying an associative retrieval framework and related spreading activation algorithms to explore transitive associations among consumers through their past transactions and feedback. Such transitive associations are a valuable source of information to help infer consumer interests and can be explored to deal with the sparsity problem. To evaluate the effectiveness of our approach, we have conducted an experimental study using a data set from an online bookstore. We experimented with three spreading activation algorithms including a constrained Leaky Capacitor algorithm, a branch-and-bound serial symbolic search algorithm, and a Hopfield net parallel relaxation search algorithm. These algorithms were compared with several collaborative filtering approaches that do not consider the transitive associations: a simple graph search approach, two variations of the user-based approach, and an item-based approach. Our experimental results indicate that spreading activation-based approaches significantly out-performed the other collaborative filtering methods as measured by recommendation precision, recall, the F-measure, and the rank score. We also observed the over-activation effect of the spreading activation approach, that is, incorporating transitive associations with past transactional data that is not sparse may {"}dilute{"} the data used to infer user preferences and lead to degradation in recommendation performance.",
keywords = "Associative retrieval, Collaborative filtering, Recommender system, Sparsity problem, Spreading activation",
author = "Zan Huang and Hsinchun Chen and Dajun Zeng",
year = "2004",
month = "1",
doi = "10.1145/963770.963775",
language = "English (US)",
volume = "22",
pages = "116--142",
journal = "ACM Transactions on Information Systems",
issn = "1046-8188",
publisher = "Association for Computing Machinery (ACM)",
number = "1",

}

TY - JOUR

T1 - Applying associative retrieval techniques to alleviate the sparsity problem in collaborative filtering

AU - Huang, Zan

AU - Chen, Hsinchun

AU - Zeng, Dajun

PY - 2004/1

Y1 - 2004/1

N2 - Recommender systems are being widely applied in many application settings to suggest products, services, and information items to potential consumers, Collaborative filtering, the most successful recommendation approach, makes recommendations based on past transactions and feedback from consumers sharing similar interests. A major problem limiting the usefulness of collaborative filtering is the sparsity problem, which refers to a situation in which transactional or feedback data is sparse and insufficient to identify similarities in consumer interests. In this article, we propose to deal with this sparsity problem by applying an associative retrieval framework and related spreading activation algorithms to explore transitive associations among consumers through their past transactions and feedback. Such transitive associations are a valuable source of information to help infer consumer interests and can be explored to deal with the sparsity problem. To evaluate the effectiveness of our approach, we have conducted an experimental study using a data set from an online bookstore. We experimented with three spreading activation algorithms including a constrained Leaky Capacitor algorithm, a branch-and-bound serial symbolic search algorithm, and a Hopfield net parallel relaxation search algorithm. These algorithms were compared with several collaborative filtering approaches that do not consider the transitive associations: a simple graph search approach, two variations of the user-based approach, and an item-based approach. Our experimental results indicate that spreading activation-based approaches significantly out-performed the other collaborative filtering methods as measured by recommendation precision, recall, the F-measure, and the rank score. We also observed the over-activation effect of the spreading activation approach, that is, incorporating transitive associations with past transactional data that is not sparse may "dilute" the data used to infer user preferences and lead to degradation in recommendation performance.

AB - Recommender systems are being widely applied in many application settings to suggest products, services, and information items to potential consumers, Collaborative filtering, the most successful recommendation approach, makes recommendations based on past transactions and feedback from consumers sharing similar interests. A major problem limiting the usefulness of collaborative filtering is the sparsity problem, which refers to a situation in which transactional or feedback data is sparse and insufficient to identify similarities in consumer interests. In this article, we propose to deal with this sparsity problem by applying an associative retrieval framework and related spreading activation algorithms to explore transitive associations among consumers through their past transactions and feedback. Such transitive associations are a valuable source of information to help infer consumer interests and can be explored to deal with the sparsity problem. To evaluate the effectiveness of our approach, we have conducted an experimental study using a data set from an online bookstore. We experimented with three spreading activation algorithms including a constrained Leaky Capacitor algorithm, a branch-and-bound serial symbolic search algorithm, and a Hopfield net parallel relaxation search algorithm. These algorithms were compared with several collaborative filtering approaches that do not consider the transitive associations: a simple graph search approach, two variations of the user-based approach, and an item-based approach. Our experimental results indicate that spreading activation-based approaches significantly out-performed the other collaborative filtering methods as measured by recommendation precision, recall, the F-measure, and the rank score. We also observed the over-activation effect of the spreading activation approach, that is, incorporating transitive associations with past transactional data that is not sparse may "dilute" the data used to infer user preferences and lead to degradation in recommendation performance.

KW - Associative retrieval

KW - Collaborative filtering

KW - Recommender system

KW - Sparsity problem

KW - Spreading activation

UR - http://www.scopus.com/inward/record.url?scp=3042819722&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=3042819722&partnerID=8YFLogxK

U2 - 10.1145/963770.963775

DO - 10.1145/963770.963775

M3 - Article

AN - SCOPUS:3042819722

VL - 22

SP - 116

EP - 142

JO - ACM Transactions on Information Systems

JF - ACM Transactions on Information Systems

SN - 1046-8188

IS - 1

ER -