A New Personalized POI Recommendation Based on Time-Aware and Social Influence

  • Nan Wang
  • Yong Liu
  • Peiyao Han
  • Xiaokun LiEmail author
  • Jinbao LiEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12403)


With the rapid growth of the location-based social networks (LBSNs), Point of Interest (POI) recommendation has become an important research topic in data mining. However, the existing works do not reasonably utilize the time sensitivity of POI recommendations and have not taken full account of the user’s behavior preferences at different time, causing the POI recommendation performance poor. We propose a Time-aware and POI Recommendation model based on Tensor Factorization, named TPR-TF. Firstly, we study the POI recommendation problem of time sensitivity and propose a temporal dynamic segmentation algorithm based on hierarchical clustering. Through dividing the fine grain of time, the experiment result is more reasonable and effectively than the previous method which divided identical time empirically. Secondly, by combining the time-aware recommendation with the influence of the user’s direct friendship and potential friendship, we expand the scope of users’ social influence, and then further improve the POI recommendation performance. Experimental results on the two datasets indicate that our TPR-TF model is superior to the current mainstream POI recommendation models both in precision and recall.


POI Time-aware Recommendation 


  1. 1.
    Guo, L., Wen, Y., Liu, F.: Location perspective-based neighborhood-aware POI recommendation in location-based social networks. Soft Comput. 23, 11935–11945 (2019). Scholar
  2. 2.
    He, J., Li, X., Liao, L., et al.: Next point-of-interest recommendation via a category-aware listwise Bayesian personalized ranking. J. Comput. Sci. 28, 206–216 (2018)CrossRefGoogle Scholar
  3. 3.
    Huang, H., Dong, Y., Tang, J., et al.: Will triadic closure strengthen ties in social networks. ACM Trans. Knowl. Discov. Data 12(3), 1–25 (2018)CrossRefGoogle Scholar
  4. 4.
    Shu-Dong, L., Xiang-Wu, M.: Recommender systems in location-based social networks. Chin. J. Comput. 38, 322–336 (2015)Google Scholar
  5. 5.
    Ye, M., Liu, X., Lee, W., et al.: Exploring social influence for recommendation: a generative model approach. In: International ACM SIGIR Conference on Research and Development in Information Retrieval 2012, pp. 671–680 (2012)Google Scholar
  6. 6.
    Gao, H., Tang, J., Hu, X., et al.: Exploring temporal effects for location recommendation on location-based social networks. In: Conference on Recommender Systems 2013, pp. 93–100 (2013)Google Scholar
  7. 7.
    Yuan, Q., Cong, G., Ma, Z., et al.: Time-aware point-of-interest recommendation. In: International ACM SIGIR Conference on Research and Development in Information Retrieval 2013, pp. 363–372 (2013)Google Scholar
  8. 8.
    Yuan, Q., Cong, G., Sun, A., et al.: Graph-based point-of-interest recommendation with geographical and temporal influences. In: Conference on Information and Knowledge Management 2014, pp. 659–668 (2014)Google Scholar
  9. 9.
    Zhang, W., Wang, J.: Location and time aware social collaborative retrieval for new successive point-of-interest recommendation. In: Conference on Information and Knowledge Management 2015, pp. 1221–1230 (2015)Google Scholar
  10. 10.
    Yao, Z., Fu, Y., Liu, B., et al.: POI recommendation: a temporal matching between poi popularity and user regularity. In: International Conference on Data Mining 2016, Barcelona, pp. 549–558 (2016)Google Scholar
  11. 11.
    Jamali, M., Ester, M.: A matrix factorization technique with trust propagation for recommendation in social networks. In: Conference on Recommender Systems 2010, pp. 135–142 (2010)Google Scholar
  12. 12.
    Hao, M.A., Zhou, T.C., Lyu, M.R., et al.: Improving recommender systems by incorporating social contextual information. ACM Trans. Inf. Syst. 29(2), 77–100 (2011)Google Scholar
  13. 13.
    Bin, C., Gu, T., Sun, Y., Chang, L.: A personalized POI route recommendation system based on heterogeneous tourism data and sequential pattern mining. Multimed. Tools Appl. 78(24), 35135–35156 (2019). Scholar
  14. 14.
    Wu, L., Sun, P., Hong, R., et al.: SocialGCN: An Efficient Graph Convolutional Network based Model for Social Recommendation., July 2019
  15. 15.
    Guo, J., Zhang, W., Fan, W., et al.: Combining geographical and social influences with deep learning for personalized point-of-interest recommendation. J. Manag. Inf. Syst. 35(4), 1121–1153 (2018)CrossRefGoogle Scholar
  16. 16.
    Rendle, S., Freudenthaler, C., Gantner, Z., et al.: BPR: Bayesian personalized ranking from implicit feedback. In: Uncertainty in Artificial Intelligence 2009, Montreal, pp. 452–461 (2009)Google Scholar
  17. 17.
    Li, H., Diao, X., Cao, J., et al.: Tag-aware recommendation based on Bayesian personalized ranking and feature mapping. Intell. Data Anal. 23(3), 641–659 (2019)CrossRefGoogle Scholar
  18. 18.
    Ma, H., Zhou, D., Liu, C., et al.: Recommender systems with social regularization. In: Web Search and Data Mining 2011, pp. 287–296 (2011)Google Scholar
  19. 19.
    Li, X., Cong, G., Li, X., et al.: Rank-GeoFM: a ranking based geographical factorization method for point of interest recommendation. In: International ACM SIGIR Conference on Research and Development in Information Retrieval 2015, pp. 433–442 (2015)Google Scholar
  20. 20.
    Hosseini, S., Li, L.T.: Point-of-interest recommendation using temporal orientations of users and locations. In: Navathe, S., Wu, W., Shekhar, S., Du, X., Wang, X., Xiong, H. (eds.) DASFAA 2016. LNCS, vol. 9642, pp. 330–347. Springer, Cham (2016). Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.School of Computer Science and TechnologyHeilongjiang UniversityHarbinChina
  2. 2.Heilongjiang Hengxun Technology Co., Ltd.HarbinChina

Personalised recommendations