Journal of Computer Science and Technology ›› 2018, Vol. 33 ›› Issue (6): 1219-1230.doi: 10.1007/s11390-018-1883-7

Special Issue: Artificial Intelligence and Pattern Recognition; Data Management and Data Mining

• Data Management and Data Mining • Previous Articles     Next Articles

Time and Location Aware Points of Interest Recommendation in Location-Based Social Networks

Tie-Yun Qian1, Member, CCF, ACM, IEEE, Bei Liu1, Liang Hong2,*, Senior Member, CCF, Member, ACM, IEEE, Zhen-Ni You1   

  1. 1. School of Computer Science, Wuhan University, Wuhan 430072, China;
    2. School of Information Management, Wuhan University, Wuhan 430072, China
  • Received:2017-08-27 Revised:2018-09-21 Online:2018-11-15 Published:2018-11-15
  • Contact: Liang Hong,E-mail:hong@whu.edu.cn E-mail:hong@whu.edu.cn
  • About author:Tie-Yun Qian received her Ph.D. degree in computer science from Huazhong University of Science and Technology, Wuhan, in 2006. She is a professor and Ph.D. supervisor at Wuhan University, Wuhan. Her research interests include Web mining, data management, etc. She has published over 40 papers on leading journals and conferences like ACL, EMNLP, COLING, SIGIR, CIKM, and INS. She is a member of CCF, ACM, and IEEE.
  • Supported by:
    This work was supported by the National Natural Science Foundation of China under Grant Nos. 61572376 and 91646206, and the National Key Research and Development Program of China under Grant No. 2016YFB1000603.

The wide spread of location-based social networks brings about a huge volume of user check-in data, which facilitates the recommendation of points of interest (POIs). Recent advances on distributed representation shed light on learning low dimensional dense vectors to alleviate the data sparsity problem. Current studies on representation learning for POI recommendation embed both users and POIs in a common latent space, and users' preference is inferred based on the distance/similarity between a user and a POI. Such an approach is not in accordance with the semantics of users and POIs as they are inherently different objects. In this paper, we present a novel translation-based, time and location aware (TransTL) representation, which models the spatial and temporal information as a relationship connecting users and POIs. Our model generalizes the recent advances in knowledge graph embedding. The basic idea is that the embedding of a pair corresponds to a translation from embeddings of users to POIs. Since the POI embedding should be close to the user embedding plus the relationship vector, the recommendation can be performed by selecting the top-k POIs similar to the translated POI, which are all of the same type of objects. We conduct extensive experiments on two real-world datasets. The results demonstrate that our TransTL model achieves the state-of-the-art performance. It is also much more robust to data sparsity than the baselines.

Key words: point of interest (POI) recommendation; location-based social network (LBSN); time and location aware;

[1] Cheng C, Yang H Q, King I, Lyu M R. A unified point-ofinterest recommendation framework in location-based social networks. ACM Transactions on Intelligent Systems and Technology, 2016, 8(1):Article No. 10.
[2] Zhu W Y, Peng W C, Chen L J, Zheng K, Zhou X F. Modeling user mobility for location promotion in location-based social networks. In Proc. the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 2015, pp.1573-1582.
[3] Chen X F, Zeng Y F, Cong G, Qin S C, Xiang Y P, Dai Y S. On information coverage for location category based point-of-interest recommendation. In Proc. the 29th AAAIConference on Artificial Intelligence, January 2015, pp.37-43.
[4] Gao H J, Tang J L, Hu X, Liu H. Content-aware point of interest recommendation on location-based social networks. In Proc. the 29th AAAI Conference on Artificial Intelligence, January 2015, pp.1721-1727.
[5] Qiao S J, Han N, Zhou J L, Li R H, Jin C Q, Gutierrez L A. SocialMix:A familiarity-based and preference-aware location suggestion approach. Engineering Applications of Artificial Intelligence, 2018, 68:192-204.
[6] Lin Y K, Liu Z Y, Sun M S, Liu Y, Zhu X. Learning entity and relation embeddings for knowledge graph completion. In Proc. the 29th AAAI Conference on Artificial Intelligence, January 2015, pp.2181-2187.
[7] He R N, Kang W C, McAuley J. Translation-based recommendation. In Proc. the 11th ACM Conference on Recommender Systems, August 2017, pp.161-169.
[8] Bordes A, Glorot X, Weston J, Bengio Y. A semantic matching energy function for learning with multi-relational data. Machine Learning, 2014, 94(2):233-259.
[9] Zheng Y, Zhang L Z, Xie X, Ma W Y. Mining interesting locations and travel sequences from GPS trajectories. In Proc. the 18th International Conference on World Wide Web, April 2009, pp.791-800.
[10] Ye M, Yin P F, Lee W C. Location recommendation for location-based social networks. In Proc. the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems, November 2010, pp.458-461.
[11] Cho E, Myers S A, Leskovec J. Friendship and mobility:User movement in location-based social networks. In Proc. the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 2011, pp.1082-1090.
[12] Yan B, Janowicz K, Mai G, Gao S. From ITDL to place2Vec -Reasoning about place type similarity and relatedness by learning embeddings from augmented spatial contexts. In Proc. the 25th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, November 2017, Article No. 35.
[13] Ye M, Yin P F, Lee W C, Lee D L. Exploiting geographical influence for collaborative point-of-interest recommendation. In Proc. the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval, July 2011, pp.325-334.
[14] Cheng C, Yang H Q, King I, Lyu M R. Fused matrix factorization with geographical and social influence in locationbased social networks. In Proc. the 26th AAAI Conference on Artificial Intelligence, July 2012, pp.17-23.
[15] Lian D F, Zhao C, Xie X, Sun G Z, Chen E H, Rui Y. GeoMF:Joint geographical modeling and matrix factorization for point-of-interest recommendation. In Proc. the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 2014, pp.831-840.
[16] Ye M, Janowicz K, Mülligann C, Lee W C. What you are is when you are:The temporal dimension of feature types in location-based social networks. In Proc. the 19th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, November 2011, pp.102-111.
[17] Yuan Q, Cong G, Ma Z Y, Sun A X, Thalmann N M. Timeaware point-of-interest recommendation. In Proc. the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval, July 2013, pp.363-372.
[18] Cheng C, Yang H Q, Lyu M R, King I. Where you like to go next:Successive point-of-interest recommendation. In Proc. the 23rd International Joint Conference on Artificial Intelligence, August 2013, pp.2605-2611.
[19] Zhao S L, Lyu M R, King I. Aggregated temporal tensor factorization model for point-of-interest recommendation. In Proc. the 23rd International Conference on Neural Information Processing, October 2016, pp.450-458.
[20] Zhao S L, King I, Lyu M R. Geo-pairwise ranking matrix factorization model for point-of-interest recommendation. In Proc. the 24th International Conference on Neural Information Processing, November 2017, pp.368-377.
[21] Feng S S, Li X T, Zeng Y F, Cong G, Chee Y M, Yuan Q. Personalized ranking metric embedding for next new POI recommendation. In Proc. the 24th International Conference on Artificial Intelligence, July 2015, pp.2069-2075.
[22] Xie M, Yin H Z, Wang H, Xu F J, Chen W T, Wang S. Learning graph-based POI embedding for location-based recommendation. In Proc. the 25th ACM International on Conference on Information and Knowledge Management, October 2016, pp.15-24.
[23] Zhao S L, Zhao T, Yang H Q, Lyu M R, King I. STELLAR:Spatial-temporal latent ranking for successive pointof-interest recommendation. In Proc. the 30th AAAI Conference on Artificial Intelligence, February 2016, pp.315-322.
[24] Zhao S L, Zhao T, King I, Lyu M R. Geo-teaser:Geotemporal sequential embedding rank for point-of-interest recommendation. In Proc. the 26th International Conference on WWW, April 2017, pp.153-162.
[25] Wang Z, Zhang J W, Feng J L, Chen Z. Knowledge graph embedding by translating on hyperplanes. In Proc. the 28th AAAI Conference on Artificial Intelligence, July 2014, pp.1112-1119.
[26] Yin H Z, Zhou X F, Cui B, Wang H, Zheng K, Hung N Q. Adapting to user interest drift for POI recommendation. IEEE Transactions on Knowledge and Data Engineering, 2016, 28(10):2566-2581.
[27] Yin H, Zhou X F, Shao Y X, Wang H, Sadiq S. Joint modeling of user check-in behaviors for point-of-interest recommendation. In Proc. CIKM, October 2015, pp.1631-1640.
[28] Wang W Q, Yin H Z, Chen L, Sun Y Z, Sadiq S, Zhou X F. Geo-SAGE:A geographical sparse additive generative model for spatial item recommendation. In Proc. the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 2015, pp.1255-1264.
[29] Tang J, Qu M, Wang M Z, Zhang M, Yan J, Mei Q Z. LINE:Large-scale information network embedding. In Proc. the 24th International Conference on WWW, May 2015, pp.1067-1077.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] Liao Xianzhi; Jin Lan;. Rendezvous Facilities in a Distributed Computer System[J]. , 1995, 10(2): 188 -192 .
[2] Fu Yuxi;. Reaction Graph[J]. , 1998, 13(6): 510 -530 .
[3] LI Xiaoshan;. Decidability of Mean Value Calculus[J]. , 1999, 14(2): 173 -180 .
[4] Cliff Reader. AVS Intellectual Property Rights (IPR) Policy[J]. , 2006, 21(3): 306 -309 .
[5] Wen Zheng, Jun-Hai Yong, and Jean-Claude Paul. Visual Simulation of Multiple Unmixable Fluids[J]. , 2007, 22(1): 156 -160 .
[6] Pierre Bourque, Serge Oligny, Alain Abran, and Bertrand Fournier. Developing Project Duration Models in Software Engineering[J]. , 2007, 22(3): 348 -357 .
[7] Bao-Dong Qin, Ming Li, and Fan-Yu Kong. Cryptanalysis of a Type of CRT-Based RSA Algorithms[J]. , 2008, 23(2): 214 -221 .
[8] Hai Zhao and Chunyu Kit. Scaling Conditional Random Fields by One-Against-the-Other Decomposition[J]. , 2008, 23(4 ): 612 -619 .
[9] Yong-Qin Huang, Senior Member, CCF, Hong-Liang Li, Xiang-Hui Xie, Lei Qian, Zi-Yu Hao, Feng Guo, and Kun Zhang. ArchSim: A System-Level Parallel Simulation Platform for the Architecture Design of High Performance Computer[J]. , 2009, 24(5): 901 -912 .
[10] Arianna D'Ulizia, Fernando Ferri, Anna Formica, and Patrizia Grifoni. Approximating Geographical Queries[J]. , 2009, 24(6): 1109 -1124 .

ISSN 1000-9000(Print)

         1860-4749(Online)
CN 11-2296/TP

Home
Editorial Board
Author Guidelines
Subscription
Journal of Computer Science and Technology
Institute of Computing Technology, Chinese Academy of Sciences
P.O. Box 2704, Beijing 100190 P.R. China
Tel.:86-10-62610746
E-mail: jcst@ict.ac.cn
 
  Copyright ©2015 JCST, All Rights Reserved