Adaptive course recommendation in MOOCs

作者：

Highlights：

• We propose a DARL framework to improve the adaptivity of course recommendation.

• We design a dynamic attention mechanism to track the changes in users’ preferences.

• Empirical results show that DARL significantly outperforms competitive baselines.

摘要

•We propose a DARL framework to improve the adaptivity of course recommendation.•We design a dynamic attention mechanism to track the changes in users’ preferences.•Empirical results show that DARL significantly outperforms competitive baselines.

论文关键词：Recommender systems,Course recommendation,Attention mechanism,Reinforcement learning

论文评审过程：Received 30 December 2020, Revised 25 March 2021, Accepted 26 April 2021, Available online 28 April 2021, Version of Record 10 May 2021.

论文官网地址：https://doi.org/10.1016/j.knosys.2021.107085