Modeling recommender systems via weighted bipartite network. (3rd August 2016)

• Record Type: Journal Article
• Authors: Xia, Jianxun; Wu, Fei; Xiong, Zenggang; Qiu, Meikang; Xie, Changsheng
• Other Names: Hassan Houcine guestEditor.; Yang Laurence T. guestEditor.; Qiu Meikang guestEditor.
• Is Part Of: Concurrency and computation. Volume 29:Number 14(2017)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2016-08-03
• Subjects: recommender systems -- bipartite network -- weighted bipartite network -- personalized recommendation; Parallel processing (Electronic computers) -- Periodicals; Parallel computers -- Periodicals; 004.35
• DOI: 10.1002/cpe.3895
• Languages: English
• ISSNs: 1532-0626

Abstract

Summary: Recommender systems have shown great potential to address information overload problems, namely, to help users find interesting and relevant objects within a huge information space. To achieve more accurate recommendation, in this paper, we proposed a recommendation algorithm Improved weighted Network‐Based Inference (INBIw) that improves on the original weighted network‐based inference by introducing a tunable parameter β to depress the influence of high‐degree nodes. In order to evaluate the recommendation performance of INBIw, ranking position rate and hitting rate are calculated. The results of experiment based on MovieLens data set show that the INBIw outperforms previous methods, including the global ranking method, collaborative filtering, network‐based inference, and weighted network‐based inference with respect to ranking position rate and hitting rate. Specifically, it performs well and gives a more accurate prediction. After further analysis, we discovered that the recommendation results of INBIw are insensitive to the amount of data and length of the recommendation list. Thus, INBIw can deal with data sparsity and is able to satisfy the varied requirements of real situations. Copyright © 2016 John Wiley & Sons, Ltd.