Abstract
Traditional collaborative filtering methods perform poorly in providing location recommendations due to the high sparsity of users’ check-in data, prompting the development of new location recommendation approaches that can integrate situational factors such as time and location. Using long short-term memory (LSTM) neural networks and kernel density estimation (KDE), this paper integrates the impact of point-of-interest (POI) location and category on users’ check-in behavior according to check-in sequence data. First, LSTM neural networks are used to model users’ periodic and repetitive daily activities for a sequence-based prediction of the probability of whether the user will visit a candidate POI. Second, the user’s geographical preference in the two-dimensional space is represented by KDE and used to make a location-based check-in probability prediction. Next, the user’s category preference is used to predict the check-in probability of a candidate POI. Finally, a user preference model is constructed from three perspectives of time, location, and category, and the comprehensive check-in probability is used for Top-N recommendation. The validation experiments on Foursquare dataset verifies that, in terms of recommendation precision and recall, the proposed recommendation method is superior to both the basic LSTM approach and the method that uses only location information. In addition, it is experimentally confirmed that the geographical preference, which is reflected by “clustering” of a user’s check-in locations, is stable, but the user’s category preference is prone to drift.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Chen J, Li X, Cheung WK et al (2016) Neurocomputing effective successive POI recommendation inferred with individual behavior and group preference. Neurocomputing 210:174–184. https://doi.org/10.1016/j.neucom.2015.10.146
Cheng C, Yang H, King I et al (2016) A unified point-of-interest recommendation framework in location-based social networks. Acm Transact Intell Syst Technol 8(1):10. https://doi.org/10.1145/2901299
De HTTH, Kao HY (2019) C-3PO: Click-sequence-aware deeP neural network (DNN)-based Pop-uPs recOmmendation: I know you’ll click. Soft Comput. https://doi.org/10.1007/s00500-018-03730-5
Kurashima T, Iwata T, Hoshide T et al (2013) Geo topic model: joint modeling of user’ s activity area and interests for location recommendation. Proc Sixth ACM Int Conf Web Search Data Min. https://doi.org/10.1145/2433396.2433444
Li H, Ge Y, Hong R et al (2016a) Point-of-interest recommendations: learning potential check-ins from friends. Proc 22nd ACM SIGKDD Int Conf Knowl Discov Data Min. https://doi.org/10.1145/2939672.2939767
Li L, Xing X, Xia H, Huang X (2016b) Entropy-Weighted instance matching between different sourcing points of interest. Entropy 18(2):1–15. https://doi.org/10.3390/e18020045
Li XIN, Jiang M, Hong H et al (2017) A time-aware personalized point-of-interest recommendation via high-order tensor factorization. ACM Transact Inf Syst 35(4):1–23. https://doi.org/10.1145/3057283
Li M, Li Y, Lou W et al (2020) A hybrid recommendation system for Q & A documents. Expert Syst Appl 144:113088. https://doi.org/10.1016/j.eswa.2019.113088
Lian D, Zhao C, Xie X et al (2014) GeoMF: joint geographical modeling and matrix factorization for point-of-interest recommendation. Proc SIGKDD. https://doi.org/10.1145/2623330.2623638
Liao J, Tang J, Zhao X, Shang H (2018) Improving POI recommendation via dynamic tensor completion. Sci Program 2018:1–11. https://doi.org/10.1155/2018/3907804
Liu Y, Wei W, Sun A et al (2014) Exploiting Geographical Neighborhood Characteristics for Location Recommendation. Proc 23rd ACM Int Conf Conf Inf Knowl Manage. https://doi.org/10.1145/2661829.2662002
Liu B, Xiong H, Member S et al (2015) A general geographical probabilistic factor model for point of interest recommendation. IEEE Trans Knowl Data Eng 27(5):1167–1179. https://doi.org/10.1109/TKDE.2014.2362525
Luo X, Zhou M, Li S et al (2015) An efficient second-order approach to factorize sparse matrices in recommender systems. IEEE Trans Industr Inf 11(4):946–956. https://doi.org/10.1109/TII.2015.2443723
Luo X, Zhou M, Xia Y et al (2016) Generating highly accurate predictions for missing QoS data via aggregating nonnegative latent factor models. IEEE Transact Neural Netw Learn Syst 27(3):524–537. https://doi.org/10.1109/TNNLS.2015.2412037
Luo X, Wang Z, Shang M (2019a) An instance-frequency-weighted regularization scheme for non-negative latent factor analysis on high-dimensional and sparse data. IEEE Transact Syst Man Cybern Syst. https://doi.org/10.1109/TSMC.2019.2930525
Luo X, Zhou M, Li S et al (2019b) Algorithms of unconstrained non-negative latent factor analysis for recommender systems. IEEE Transact Big Data. https://doi.org/10.1109/TBDATA.2019.2916868
Nassar N, Jafar A, Rahhal Y (2020) Knowledge-Based Systems A novel deep multi-criteria collaborative filtering model for recommendation system. Knowl Based Syst 187:104811. https://doi.org/10.1016/j.knosys.2019.06.019
Quadrana M, Milano P, Karatzoglou A et al (2017) Personalizing session-based recommendations with hierarchical recurrent neural networks. Proc Eleventh ACM Conf Recomm Syst. https://doi.org/10.1145/3109859.3109896
Rendle S, Freudenthaler C, Schmidt-thieme L (2010) Factorizing personalized markov chains for next-basket recommendation. Proc 19th Int Conf World Wide Web. https://doi.org/10.1145/1772690.1772773
Uddin S, Habibullah T (2020) Framework of dynamic recommendation system for e-shopping. Int J Inf Technol 12(1):135–140. https://doi.org/10.1007/s41870-019-00388-6
Van MB, Fellow CS (2014) Learning phrase representations using RNN encoder—decoder for statistical machine translation. Comput Sci. https://doi.org/10.3115/v1/D14-1179
Wang F, Qu Y, Zheng L et al (2017) Deep and broad learning on content-aware POI recommendation. 2017 IEEE 3rd Int Conf Collab Internet Comput (CIC). https://doi.org/10.1109/CIC.2017.00054
Xia B, Li Y, Li Q, Li T (2017) Attention-based recurrent neural network for location recommendation. 12th Int Conf Intell Syst Knowl Eng (ISKE). https://doi.org/10.1109/ISKE.2017.8258747
Ye M, Yin P, Lee W et al (2011) Exploiting geographical influence for collaborative point-of-interest recommendation. Proc 34th Int ACM SIGIR Conf Res Dev Inf Retr. https://doi.org/10.1145/2009916.2009962
Zeng W, Fu CW, Arisona SM et al (2017) Visualizing the relationship between human mobility and points of interest. IEEE Trans Intell Transp Syst 18(8):2271–2284. https://doi.org/10.1109/TITS.2016.2639320
Zhang J, Chow C (2013) iGSLR : personalized geo-social location recommendation—a kernel density estimation approach. Proc 21st ACM SIGSPATIAL Int Conf Adv Geogr Inf Syst. https://doi.org/10.1145/2525314.2525339
Zhang J, Chow C (2014) CoRe: exploiting the personalized influence of two-dimensional geographic coordinates for location recommendations. Inf Sci 293:163–181. https://doi.org/10.1016/j.ins.2014.09.014
Zhang J, Chow C (2015a) GeoSoCa: exploiting geographical, social and categorical correlations for point-of-interest recommendation. Proc 38th Int ACM SIGIR Conf Res Dev Inf Retr. https://doi.org/10.1145/2766462.2767711
Zhang J, Chow C (2015b) Spatiotemporal sequential influence modeling for location recommendations: a gravity-based approach. Acm Transact Int Syst Technol 7(1):1–25. https://doi.org/10.1145/2786761
Zhang J, Chow C (2016) TICRec: a probabilistic framework to utilize temporal influence correlations for time-aware location recommendations. IEEE Trans Serv Comput 9(4):633–646. https://doi.org/10.1109/TSC.2015.2413783
Zhang J, Chow C, Li Y (2014a) LORE: exploiting sequential influence for location recommendations. Sigspatial. https://doi.org/10.1145/2666310.2666400
Zhang J, Chow C, Li Y (2014b) iGeoRec: a personalized and efficient geographical location recommendation framework. IEEE Trans Serv Comput. https://doi.org/10.1109/TSC.2014.2328341
Zhang L, Hu T, Min Y et al (2017) A taxi order dispatch model based on combinatorial optimization. 23rd ACM SIGKDD Int Conf. https://doi.org/10.1145/3097983.3098138
Zhao P, Zhu H, Liu Y et al (2018) Where to go next: a spatio-temporal LSTM model for next POI recommendation. https://arxiv.org/abs/1806.06671
Funding
This work was partly funded by the National Science Foundation of China (Nos. 71871019, 71471016, 71531013, 71729001) and by the Fundamental Research Funds for the Central Universities under Grant No. FRF-TP-18-013B1.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
Author Mingxin Gan declares that she has no conflict of interest. Author Yingxue Ma declares that she has no conflict of interest.
Ethical approval
This article does not contain any studies with human participants or animals performed by any of the authors.
Additional information
Communicated by V. Loia.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Ma, Y., Gan, M. Exploring multiple spatio-temporal information for point-of-interest recommendation. Soft Comput 24, 18733–18747 (2020). https://doi.org/10.1007/s00500-020-05107-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-020-05107-z