Resolving data sparsity and cold start problem in collaborative filtering recommender system using Linked Open Data

作者：

Highlights：

• A MF model with Linked Open Data is developed to handle data sparsity issue.

• Hidden data and LOD similarity measure are integrated to enhance recommendations.

• The proposed framework can be applied to any domain for recommendations.

• Experiments were done on Netflix and Movie Lens datasets for validation.

摘要

•A MF model with Linked Open Data is developed to handle data sparsity issue.•Hidden data and LOD similarity measure are integrated to enhance recommendations.•The proposed framework can be applied to any domain for recommendations.•Experiments were done on Netflix and Movie Lens datasets for validation.

论文关键词：Collaborative filtering,Matrix factorization,Linked open data, recommender system,Data sparsity

论文评审过程：Received 8 October 2019, Revised 2 January 2020, Accepted 24 January 2020, Available online 25 January 2020, Version of Record 1 February 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113248