Topic model-based recommender systems and their applications to cold-start problems

作者：

Highlights：

• Topic models are implemented in recommender systems to solve cold start problems.

• Proposed models are based on content-based filtering and latent Dirichlet allocation.

• The proposed models outperform existing baselines in prediction accuracy.

摘要

•Topic models are implemented in recommender systems to solve cold start problems.•Proposed models are based on content-based filtering and latent Dirichlet allocation.•The proposed models outperform existing baselines in prediction accuracy.

论文关键词：Cold-start problems,Correspondence LDA,Hierarchical Dirichlet process,Joint LDA,Latent Dirichlet allocation,Probabilistic matrix decomposition,Recommender systems

论文评审过程：Received 2 September 2021, Revised 28 January 2022, Accepted 28 March 2022, Available online 9 April 2022, Version of Record 4 May 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117129