The role of context fusion on accuracy, beyond-accuracy, and fairness of point-of-interest recommendation systems

作者：

Highlights：

• The paper investigates the role of context fusion in POI recommendations.

• Evaluations of the accuracy, beyond-accuracy, and fairness of POI recommendations.

• We provide better recommendations in terms of beyond accuracy and accuracy metrics.

• The study pushes the research forward by choosing several evaluation objectives.

• The results of fairness show that contextual models provide better fairness results.

摘要

•The paper investigates the role of context fusion in POI recommendations.•Evaluations of the accuracy, beyond-accuracy, and fairness of POI recommendations.•We provide better recommendations in terms of beyond accuracy and accuracy metrics.•The study pushes the research forward by choosing several evaluation objectives.•The results of fairness show that contextual models provide better fairness results.

论文关键词：Contextual information,Context-aware POI recommendation,Interpretability,Evaluation,Fairness,Beyond-accuracy

论文评审过程：Received 21 October 2021, Revised 18 May 2022, Accepted 28 May 2022, Available online 3 June 2022, Version of Record 10 June 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117700