On the effects of aggregation strategies for different groups of users in venue recommendation
作者：
Highlights：
• Use of three different aggregation techniques in Point of interest recommendation.
• Better data is more useful than more data when aggregating several cities.
• Analysis of biases of fourteen recommenders in local and tourist users of LBSNs.
• Experiments include performance analysis of accuracy and beyond-accuracy metrics.
• An experimental setup using a temporal split in eight different cities.
摘要
•Use of three different aggregation techniques in Point of interest recommendation.•Better data is more useful than more data when aggregating several cities.•Analysis of biases of fourteen recommenders in local and tourist users of LBSNs.•Experiments include performance analysis of accuracy and beyond-accuracy metrics.•An experimental setup using a temporal split in eight different cities.
论文关键词：Venue recommendation,Data augmentation,Temporal evaluation,Tourism,User types,Fairness
论文评审过程：Received 16 November 2020, Revised 8 March 2021, Accepted 13 April 2021, Available online 18 May 2021, Version of Record 18 May 2021.
论文官网地址：https://doi.org/10.1016/j.ipm.2021.102609
