A graph-based recommender system for digital library

Abstract

Research shows that recommendations comprise a valuable service for users of a digital library [11]. While most existing recommender systems rely either on a content-based approach or a collaborative approach to make recommendations, there is potential to improve recommendation quality by using a combination of both approaches (a hybrid approach). In this paper, we report how we tested the idea of using a graph-based recommender system that naturally combines the content-based and collaborative approaches. Due to the similarity between our problem and a concept retrieval task, a Hopfield net algorithm was used to exploit high-degree book-book, useruser and book-user associations. Sample hold-out testing and preliminary subject testing were conducted to evaluate the system, by which it was found that the system gained improvement with respect to both precision and recall by combining content-based and collaborative approaches. However, no significant improvement was observed by exploiting high-degree associations.

A long-tail inspired measure to assess resource use in information services

“…Coefficient approach could be to use filtering and recommendation mechanisms (Callan & Smeaton, 2003;Huang, Chung, Ong, & Chen, 2002;Torres, McNee, Abel, Konstan, & Riedl, 2004) so as to favor long-tail items over short-tail items for library users, in order to increase the demand, and thus reduce the value of the Gini index. Empirical data collection methods for the identification and classification of libraries and collections in the demand categories have been suggested.…”

Densifying a behavioral recommender system by social networks link prediction methods

“…Huang et al (2002) propose a two-layer graph-based recommender system in the context of digital libraries. Books and users represent layer nodes and the edges represent transactions.…”

Does a one-size recommendation system fit all? the effectiveness of collaborative filtering based recommendation systems across different domains and search modes

“…heterogeneous domains). Huang et al [2002] and Torres et al [2004] found that as more rating data are used as the input for generating recommendations, the accuracy of the recommendations decreased. For example, Torres et al [2004] used reference lists at the end of research papers as users' ratings.…”

“…First, CF has been used mostly for consumer products, such as CDs, books, and movies [Wingfield 1998] and has only recently been applied to other areas, such as research papers and digital libraries [Huang et al 2002;McNee et al 2002;Torres et al 2004]. In fact, CF is thought to have much potential for improving the information search in digital libraries [Williams 2002].…”