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

By Zan Huang, Hsinchun Chen, Daniel Dajun Zeng. TOIS, 2004

713 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/989e1b44dee256dfb4be003b3207ca66e2bed3ca

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Information Systems

In Management Science and Operations Research

Citations in the corpus

Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions (2005, background): “Another approach that also explores similarities among users has been proposed in [49], where the sparsity problem is addressed by applying associative retrieval framework and related spreading activation algorithms to explore transitive associations among consumers through their past transactions…”
Recommender Systems (2012, methodology): “Hence, an effective recommender algorithm must take the data sparsity into account [27].”
Link prediction approach to collaborative filtering (2005, methodology): “For comparison purposes, we included standard user-based and item-based collaborative filtering algorithms as benchmarks [3].”
Diversity in recommender systems - A survey (2017, background): “Regardless of the content type and/or recommendation all RSs face the problem of data sparsity [34] : working with user-item datasets that are mostly empty.”
Recommender systems with social regularization (2011, methodology): “As mentioned in [10], one of the most commonly-used and successfully-deployed recommendation approaches is collaborative filtering.”
Exploiting geographical influence for collaborative point-of-interest recommendation (2011, methodology): “(6) How well our techniques deal with cold start users, who do not have many check-in records for discovery of their interests [10].”
Classification in Networked Data: A Toolkit and a Univariate Case Study (2007, positive): “For marketing, consumers can be connected into a network based on the products that they buy (or that they rate in a collaborative ﬁltering system), and then network-based techniques can be applied for making product recommendations (Domingos and Richardson, 2001; Huang et al., 2004).”
Scalable collaborative filtering using cluster-based smoothing (2005, methodology): “By considering the association between users and items, transitive associations of the associative-retrieval technique [11] are proposed to iteratively reinforce the similarity of the users and the similarity of items.”
A Distributed, Architecture-Centric Approach to Computing Accurate Recommendations from Very Large and Sparse Datasets (2011, result): “In fact, previous research shows that the item-based approach produces more accurate results [70, 94, 142, 145, 148] because item vectors”
Inferring Latent Network from Cascade Data for Dynamic Social Recommendation (2016, background): “Social relations can be trust relations, friendships, memberships or following relations and so on [20] [10].”
Alleviating the Sparsity Problem of Collaborative Filtering Using Trust Inferences (2005, methodology): “Transitive associations of the associative retrieval technique [11], even if they have been successfully employed to deal with the sparsity problem, fail to express the subjective notion of the associations.”
A new similarity measure for collaborative filtering to alleviate the new user cold-starting problem (2008, background): “All the studies, to the best of the author’s knowledge, present hybrid recommender systems that combine both content information and ratings data [10,16,25,27,30] to circumvent the problem, where usually content-based similarity is used for new users or new items for whom ratings-based similarity ca”
Recommender Systems (2016, neutral): “A method, which uses the number of discounted paths between a pair of nodes in a user-item graph for recommendations, was proposed in [262].”
Probabilistic factor models for web site recommendation (2011, methodology): “As discussed in [9], one of the most commonly-used and successfully-deployed recommendation approaches is collaborative filtering.”
A Comprehensive Survey of Neighborhood-based Recommendation Methods (2011, methodology): “The number of paths between a user and an item in a bipartite graph can also be used to evaluate their compatibility [34].”