Joint modeling of user check-in behaviors for point-of-interest recommendation

Yin, Hongzhi, Zhou, Xiaofang, Shao, Yingxia, Wang, Hao and Sadiq, Shazia (2015). Joint modeling of user check-in behaviors for point-of-interest recommendation. In: CIKM 2015 - Proceedings of the 24th ACM International Conference on Information and Knowledge Management. 24th ACM International Conference on Information and Knowledge Management, CIKM 2015, Melbourme, VIC, Australia, (1631-1640). 19-23 October, 2015. doi:10.1145/2806416.2806500


Author Yin, Hongzhi
Zhou, Xiaofang
Shao, Yingxia
Wang, Hao
Sadiq, Shazia
Title of paper Joint modeling of user check-in behaviors for point-of-interest recommendation
Conference name 24th ACM International Conference on Information and Knowledge Management, CIKM 2015
Conference location Melbourme, VIC, Australia
Conference dates 19-23 October, 2015
Convener James Bailey
Proceedings title CIKM 2015 - Proceedings of the 24th ACM International Conference on Information and Knowledge Management
Journal name International Conference on Information and Knowledge Management, Proceedings
Series International Conference on Information and Knowledge Management, Proceedings
Place of Publication New York , NY, United States
Publisher Association for Computing Machinery
Publication Year 2015
Sub-type Fully published paper
DOI 10.1145/2806416.2806500
Open Access Status Not Open Access
ISBN 9781450337946
Volume 24
Start page 1631
End page 1640
Total pages 10
Collection year 2016
Language eng
Abstract/Summary Point-of-Interest (POI) recommendation has become an important means to help people discover attractive and interesting locations, especially when users travel out of town. However, extreme sparsity of user-POI matrix creates a severe challenge. To cope with this challenge, a growing line of research has exploited the temporal effect, geographical-social influence, content effect and word-of-mouth effect. However, current research lacks an integrated analysis of the joint effect of the above factors to deal with the issue of data-sparsity, especially in the out-of-town recommendation scenario which has been ignored by most existing work. In light of the above, we propose a joint probabilistic generative model to mimic user check-in behaviors in a process of decision making, which strategically integrates the above factors to effectively overcome the data sparsity, especially for out-of-town users. To demonstrate the applicability and flexibility of our model, we investigate how it supports two recommendation scenarios in a unified way, i.e., home-town recommendation and out-of-town recommendation. We conduct extensive experiments to evaluate the performance of our model on two real large-scale datasets in terms of both recommendation effectiveness and efficiency, and the experimental results show its superiority over other competitors.
Keyword Joint modeling
Location-based service
Probabilistic generative model
Recommender system
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status UQ

 
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 9 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Tue, 15 Mar 2016, 02:46:28 EST by System User on behalf of Learning and Research Services (UQ Library)