中国邮电高校学报(英文) ›› 2016, Vol. 23 ›› Issue (4): 25-36.doi: 10.1016/S1005-8885(16)60042-0

• Networks • 上一篇    下一篇

Joint model of user check-in activities for point-of- interest recommendation

任星怡   

  1. 北京邮电大学
  • 收稿日期:2016-05-10 修回日期:2016-07-08 出版日期:2016-08-30 发布日期:2016-08-30
  • 通讯作者: 任星怡 E-mail:xyren@bupt.edu.cn

Joint model of user check-in activities for point-of- interest recommendation

Xing-Yi REN   

  1. Beijing University of Posts and Telecommunications
  • Received:2016-05-10 Revised:2016-07-08 Online:2016-08-30 Published:2016-08-30
  • Contact: Xing-Yi REN E-mail:xyren@bupt.edu.cn

摘要: With the rapid development of location-based networks, point-of-interest (POI) recommendation has become an important means to help people discover interesting and attractive locations, especially when users travel out of town. However, because users only check-in interaction is highly sparse, which creates a big challenge for POI recommendation. To tackle this challenge, we propose a joint probabilistic generative model called geographical temporal social content popularity (GTSCP) to imitate user check-in activities in a process of decision making, which effectively integrates the geographical influence, temporal effect, social correlation, content information and popularity impact factors to overcome the data sparsity, especially for out-of-town users. Our proposed the GTSCP supports two recommendation scenarios in a joint model, i.e., home-town recommendation and out-of-town recommendation. Experimental results show that GTSCP achieves significantly superior recommendation quality compared to other state-of-the-art POI recommendation techniques.

关键词: POI recommendation, user check-in activities, joint probabilistic generative model, geographical influence, social influence, temporal effect, content information, popularity information

Abstract: With the rapid development of location-based networks, point-of-interest (POI) recommendation has become an important means to help people discover interesting and attractive locations, especially when users travel out of town. However, because users only check-in interaction is highly sparse, which creates a big challenge for POI recommendation. To tackle this challenge, we propose a joint probabilistic generative model called geographical temporal social content popularity (GTSCP) to imitate user check-in activities in a process of decision making, which effectively integrates the geographical influence, temporal effect, social correlation, content information and popularity impact factors to overcome the data sparsity, especially for out-of-town users. Our proposed the GTSCP supports two recommendation scenarios in a joint model, i.e., home-town recommendation and out-of-town recommendation. Experimental results show that GTSCP achieves significantly superior recommendation quality compared to other state-of-the-art POI recommendation techniques.

Key words: POI recommendation, user check-in activities, joint probabilistic generative model, geographical influence, social influence, temporal effect, content information, popularity information