Applying Associative Retrieval Techniques to Alleviate the Sparsity Problem in Collaborative Filtering

DMCA

Applying Associative Retrieval Techniques to Alleviate the Sparsity Problem in Collaborative Filtering (2004)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Zan Huang , Hsinchun Chen , Daniel Zeng

Venue:	ACM Transactions on Information Systems
Citations:	134 - 12 self

BibTeX

@ARTICLE{Huang04applyingassociative,
    author = {Zan Huang and Hsinchun Chen and Daniel Zeng},
    title = {Applying Associative Retrieval Techniques to Alleviate the Sparsity Problem in Collaborative Filtering},
    journal = {ACM Transactions on Information Systems},
    year = {2004},
    volume = {22},
    pages = {116--142}
}

OpenURL

Abstract

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 outperformed 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

Keyphrases

sparsity problem transitive association associative retrieval technique collaborative filtering activation algorithm constrained leaky capacitor algorithm past transaction activation approach simple graph search approach branch-and-bound serial symbolic search algorithm several collaborative filtering approach associative retrieval framework online bookstore data set consumer interest recommendation performance past transactional data user-based approach user preference valuable source recommendation precision activation-based approach item-based approach rank score experimental study over-activation effect experimental result

DMCA