Multi-context embedding based personalized place semantics recognition
作者：
Highlights：
• Propose a multi-context embedding based personalized place semantics recognition method (MEPSR), which employs embedding methods, including deep learning based embedding and word embedding, to obtain effective representations from multi-context information.
• Jointly model personalized place semantics and App usage sequences by sharing the App representations, which can introduce an inductive bias to improve generalization capability.
• Conduct extensive experiments on the Mobile Data Challenge (MDC) dataset to show that MEPSR outperforms existing methods significantly.
摘要
•Propose a multi-context embedding based personalized place semantics recognition method (MEPSR), which employs embedding methods, including deep learning based embedding and word embedding, to obtain effective representations from multi-context information.•Jointly model personalized place semantics and App usage sequences by sharing the App representations, which can introduce an inductive bias to improve generalization capability.•Conduct extensive experiments on the Mobile Data Challenge (MDC) dataset to show that MEPSR outperforms existing methods significantly.
论文关键词：Personalized place semantics,Multi-context information,Embedding
论文评审过程：Received 1 July 2020, Revised 15 October 2020, Accepted 16 October 2020, Available online 24 October 2020, Version of Record 24 October 2020.
论文官网地址：https://doi.org/10.1016/j.ipm.2020.102416
