NexT: A framework for next-place prediction on location based social networks
作者：
Highlights：
• The next-location prediction problem is formally defined in LBSNs.
• New method combining sequential patterns and feature-based supervised classifier.
• Spatio-temporal features to catch mobility patterns and characteristics of locations.
• New model for sequential mobility based on sequential movements and user preference.
• Spatio-temporal analysis in three large-scale real-world social media datasets.
• Experiments show the approach is effective and outperforms state-of-the-art works.
摘要
•The next-location prediction problem is formally defined in LBSNs.•New method combining sequential patterns and feature-based supervised classifier.•Spatio-temporal features to catch mobility patterns and characteristics of locations.•New model for sequential mobility based on sequential movements and user preference.•Spatio-temporal analysis in three large-scale real-world social media datasets.•Experiments show the approach is effective and outperforms state-of-the-art works.
论文关键词：Next-place prediction,Trajectory pattern mining,LBSN
论文评审过程：Received 24 January 2020, Revised 3 June 2020, Accepted 29 June 2020, Available online 1 July 2020, Version of Record 4 July 2020.
论文官网地址：https://doi.org/10.1016/j.knosys.2020.106205
