A novel matrix factorization model for recommendation with LOD-based semantic similarity measure

作者：

Highlights：

• A MF model uses implicit feedback and semantic similarity to extend user & item vector.

• A novel semantic similarity measure which uses feature- and distance-based metrics.

• A general recommender framework. Based on it, other knowledge bases can be used.

摘要

•A MF model uses implicit feedback and semantic similarity to extend user & item vector.•A novel semantic similarity measure which uses feature- and distance-based metrics.•A general recommender framework. Based on it, other knowledge bases can be used.

论文关键词：Collaborative filtering,Matrix factorization,Implicit feedback,Semantic similarity,Linked open data,DBpedia

论文评审过程：Received 2 April 2018, Revised 8 January 2019, Accepted 9 January 2019, Available online 11 January 2019, Version of Record 15 January 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.01.036