Combining novelty and popularity on personalised recommendations via user profile learning

作者：

Highlights：

• Quality of recommendations can improve with user profile learning.

• Combining novelty and popularity generates personalised recommendations.

• Automatic tuning in diffusion-based methods allows better results on sparse data.

摘要

•Quality of recommendations can improve with user profile learning.•Combining novelty and popularity generates personalised recommendations.•Automatic tuning in diffusion-based methods allows better results on sparse data.

论文关键词：Recommender systems,Machine learning,Data sparsity,Diffusion-based algorithms,User profile

论文评审过程：Received 12 September 2019, Revised 22 November 2019, Accepted 18 December 2019, Available online 26 December 2019, Version of Record 6 January 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.113149