Full Text:   <592>

Summary:  <180>

CLC number: TP181

On-line Access: 2023-06-21

Received: 2022-07-15

Revision Accepted: 2023-09-21

Crosschecked: 2023-02-23

Cited: 0

Clicked: 991

Citations:  Bibtex RefMan EndNote GB/T7714




Zhimin LV


-   Go to

Article info.
Open peer comments

Frontiers of Information Technology & Electronic Engineering  2023 Vol.24 No.9 P.1273-1286


Exploring nonlinear spatiotemporal effects for personalized next point-of-interest recommendation

Author(s):  Xi SUN, Zhimin LV

Affiliation(s):  Collaborative Innovation Center of Steel Technology, University of Science and Technology Beijing, Beijing 100083, China

Corresponding email(s):   b20190537@xs.ustb.edu.cn, lvzhimin@nercar.ustb.edu.cn

Key Words:  Point-of-interest recommendation, Spatiotemporal effects, Long short-term memory (LSTM), Attention mechanism

Xi SUN, Zhimin LV. Exploring nonlinear spatiotemporal effects for personalized next point-of-interest recommendation[J]. Frontiers of Information Technology & Electronic Engineering, 2023, 24(9): 1273-1286.

@article{title="Exploring nonlinear spatiotemporal effects for personalized next point-of-interest recommendation",
author="Xi SUN, Zhimin LV",
journal="Frontiers of Information Technology & Electronic Engineering",
publisher="Zhejiang University Press & Springer",

%0 Journal Article
%T Exploring nonlinear spatiotemporal effects for personalized next point-of-interest recommendation
%A Zhimin LV
%J Frontiers of Information Technology & Electronic Engineering
%V 24
%N 9
%P 1273-1286
%@ 2095-9184
%D 2023
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.2200304

T1 - Exploring nonlinear spatiotemporal effects for personalized next point-of-interest recommendation
A1 - Xi SUN
A1 - Zhimin LV
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 24
IS - 9
SP - 1273
EP - 1286
%@ 2095-9184
Y1 - 2023
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.2200304

Next point-of-interest (POI) recommendation is an important personalized task in location-based social networks (LBSNs) and aims to recommend the next POI for users in a specific situation with historical check-in data. State-of-the-art studies linearly discretize the user’s spatiotemporal information and then use recurrent neural network (RNN) based models for modeling. However, these studies ignore the nonlinear effects of spatiotemporal information on user preferences and spatiotemporal correlations between user trajectories and candidate POIs. To address these limitations, a spatiotemporal trajectory (STT) model is proposed in this paper. We use the long short-term memory (LSTM) model with an attention mechanism as the basic framework and introduce the user’s spatiotemporal information into the model in encoding. In the process of encoding information, an exponential decay factor is applied to reflect the nonlinear drift of user interest over time and distance. In addition, we design a spatiotemporal matching module in the process of recalling the target to select the most relevant POI by measuring the relevance between the user’s current trajectory and the candidate set. We evaluate the performance of our STT model with four real-world datasets. Experimental results show that our model outperforms existing state-of-the-art methods.




Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article


[1]Abdollahi B, Nasraoui O, 2016. Explainable restricted Boltzmann machines for collaborative filtering.

[2]Aggarwal CC, Han JW, Wang JY, et al., 2004. A framework for projected clustering of high dimensional data streams. In: Nascimento MA, Özsu MT, Kossmann D, et al. (Eds.), Proc VLDB Conf Elsevier, Amsterdam, p.852-863.

[3]Chen KS, Xu ZH, Gong LY, 2012. Research of the distance calculation algorithm based on RSSI. Adv Mater Res, 499:464-468.

[4]Cheng HT, Koc L, Harmsen J, et al., 2016. Wide & deep learning for recommender systems. Proc 1st Workshop on Deep Learning for Recommender Systems, p.7-10.

[5]Cui Q, Tang YY, Wu S, et al., 2019. Distance2Pre: personalized spatial preference for next point-of-interest prediction. 23rd Pacific-Asia Conf on Advances in Knowledge Discovery and Data Mining, p.289-301.

[6]Fan W, 2004. Systematic data selection to mine concept-drifting data streams. Proc 10th ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining, p.128-137.

[7]Feng J, Li Y, Zhang C, et al., 2018. DeepMove: predicting human mobility with attentional recurrent networks. Proc World Wide Web Conf, p.1459-1468.

[8]Feng SS, Li XT, Zeng YF, et al., 2015. Personalized ranking metric embedding for next new POI recommendation. Proc 24th Int Conf on Artificial Intelligence, p.2069-2075.

[9]Gao HJ, Tang JL, Hu X, et al, 2013. Exploring temporal effects for location recommendation on location-based social networks. Proc 7th ACM Conf on Recommender Systems, p.93-100.

[10]Gehring J, Auli M, Grangier D, et al., 2017. Convolutional sequence to sequence learning. 34th Int Conf on Machine Learning, p.1243-1252.

[11]Guo Q, Sun Z, Zhang J, et al., 2020. An attentional recurrent neural network for personalized next location recommendation. Proc 34th AAAI Conf on Artificial Intelligence, p.83-90.

[12]He XN, Liao LZ, Zhang HW, et al., 2017. Neural collaborative filtering. Proc 26th Int Conf on World Wide Web, p.‍173-182.

[13]Hochreiter S, Schmidhuber J, 1997. Long short-term memory. Neur Comput, 9(8):1735-1780.

[14]Jiang SH, Qian XM, Shen JL, et al., 2015. Author topic model-based collaborative filtering for personalized POI recommendations. IEEE Trans Multim, 17(6):907-918.

[15]Kang WC, McAuley J, 2018. Self-attentive sequential recommendation. IEEE Int Conf on Data Mining, p.197-206.

[16]Kingma DP, Ba J, 2014. Adam: a method for stochastic optimization.

[17]Li JC, Wang YJ, McAuley J, 2020. Time interval aware self-attention for sequential recommendation. Proc 13th Int Conf on Web Search and Data Mining, p.322-330.

[18]Lian DF, Zheng VW, Xie X, 2013. Collaborative filtering meets next check-in location prediction. Proc 22nd Int Conf on World Wide Web, p.231-232.

[19]Lian DF, Wu YJ, Ge Y, et al., 2020. Geography-aware sequential location recommendation. Proc 26th ACM SIGKDD Int Conf on Knowledge Discovery & Data Mining, p.‍2009-2019.

[20]Liu Q, Wu S, Wang DY, et al., 2016a. Context-aware sequential recommendation. IEEE 16th Int Conf on Data Mining, p.1053-1058.

[21]Liu Q, Wu S, Wang L, et al., 2016b. Predicting the next location: a recurrent model with spatial and temporal contexts. Proc 30th AAAI Conf on Artificial Intelligence, p.194-200.

[22]Liu YC, Liu CR, Liu B, et al., 2016. Unified point-of-interest recommendation with temporal interval assessment. Proc 22nd ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining, p.1015-1024.

[23]Luo YT, Liu Q, Liu ZC, 2021. STAN: spatio-temporal attention network for next location recommendation. Proc Web Conf, p.2177-2185.

[24]Mikolov T, Kombrink S, et al., 2011. Extensions of recurrent neural network language model. IEEE Int Conf Acoustics Speech and Signal Processing, p.5528-5531.

[25]Qian TY, Liu B, Nguyen QVH, et al., 2019. Spatiotemporal representation learning for translation-based POI recommendation. ACM Trans Inform Syst, 37(2):1-24.

[26]Ren Z, Fang F, et al., 2022. State of the art in defect detection based on machine vision. Int J Precis Eng Manuf-Green Techn, 9(2):661-691.

[27]Rendle S, Freudenthaler C, Schmidt-Thieme L, 2010. Factorizing personalized Markov chains for next-basket recommendation. Proc 19th Int Conf on World Wide Web, p.811-820.

[28]Salakhutdinov R, Mnih A, 2007. Probabilistic matrix factorization. Proc 20th Int Conf on Neural Information Processing Systems, p.1257-1264.

[29]Si YL, Zhang FZ, Liu WY, 2019. An adaptive point-of-interest recommendation method for location-based social networks based on user activity and spatial features. Knowl-Based Syst, 163:267-282.

[30]Sun K, Qian TY, Chen T, et al., 2020. Where to go next: modeling long- and short-term user preferences for point-of-interest recommendation. Proc 34th AAAI Conf on Artificial Intelligence, p.214-221.

[31]Wang HX, Fan W, Yu PS, et al., 2003. Mining concept-drifting data streams using ensemble classifiers. Proc 9th ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining, p.226-235.

[32]Wu YX, Li K, Zhao GS, et al., 2022. Personalized long- and short-term preference learning for next POI recommendation. IEEE Trans Knowl Data Eng, 34(4):1944-1957.

[33]Xu CH, Ding AS, Zhao KD, 2021. A novel POI recommendation method based on trust relationship and spatial‍‒‍temporal factors. Electr Commer Res Appl, 48:101060.

[34]Xu S, Cao JX, Legg P, et al., 2020. Venue2Vec: an efficient embedding model for fine-grained user location prediction in geo-social networks. IEEE Syst J, 14(2):1740-1751.

[35]Yang C, Bai LX, Zhang C, et al., 2017. Bridging collaborative filtering and semi-supervised learning: a neural approach for POI recommendation. Proc 23rd ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining, p.1245-1254.

[36]Yang DQ, Zhang DQ, Zheng VW, et al., 2015. Modeling user activity preference by leveraging user spatial temporal characteristics in LBSNs. IEEE Trans Syst Man Cybern Syst, 45(1):129-142.

[37]Yang DQ, Fankhauser B, Rosso P, et al., 2020. Location prediction over sparse user mobility traces using RNNs: flashback in hidden states!Proc 29th Int Joint Conf on Artificial Intelligence, p.2184-2190.

[38]Ye M, Yin PF, Lee WC, 2010. Location recommendation for location-based social networks. Proc 18th SIGSPATIAL Int Conf on Advances in Geographic Information Systems, p.458-461.

[39]Yin HZ, Wang WQ, Wang H, et al., 2017. Spatial-aware hierarchical collaborative deep learning for POI recommendation. IEEE Trans Knowl Data Eng, 29(11):2537-2551.

[40]Ying HC, Zhuang FZ, Zhang FZ, et al., 2018. Sequential recommender system based on hierarchical attention network. Proc 27th Int Joint Conf on Artificial Intelligence, p.3926-3932.

[41]Yuan Q, Cong G, Ma ZY, et al., 2013. Time-aware point-of-interest recommendation. Proc 36th Int ACM SIGIR Conf on Research and Development in Information Retrieval, p.363-372.

[42]Yuan Q, Cong G, Sun AX, 2014. Graph-based point-of-interest recommendation with geographical and temporal influences. Proc 23rd ACM Int Conf on Information and Knowledge Management, p.659-668.

[43]Zeng J, Tang HR, Zhao YZ, et al., 2021. PR-RCUC: a POI recommendation model using region-based collaborative filtering and user-based mobile context. Mobile Netw Appl, 26(6):2434-2444.

[44]Zhang T, Zheng WM, Cui Z, et al., 2019. Spatial–temporal recurrent neural network for emotion recognition. IEEE Trans Cybern, 49(3):839-847.

[45]Zhao GS, Lou PL, Qian XM, et al., 2020. Personalized location recommendation by fusing sentimental and spatial context. Knowl-Based Syst, 196:105849.

[46]Zhao KZ, Zhang Y, Yin HZ, et al., 2020. Discovering subsequence patterns for next POI recommendation. Proc 29th Int Joint Conf on Artificial Intelligence, p.3216-3222.

[47]Zhao PP, Luo AJ, Liu YC, et al., 2022. Where to go next: a spatio-temporal gated network for next POI recommendation. IEEE Trans Knowl Data Eng, 34(5):2512-2524.

[48]Zhao SL, Zhao T, Yang HQ, et al., 2016. STELLAR: spatial-temporal latent ranking for successive point-of-interest recommendation. Proc 30th AAAI Conf on Artificial Intelligence, p.315-322.

[49]Zhao WX, Zhou NN, Sun AX, et al., 2018. A time-aware trajectory embedding model for next-location recommendation. Knowl Inform Syst, 56(3):559-579.

Open peer comments: Debate/Discuss/Question/Opinion


Please provide your name, email address and a comment

Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - 2024 Journal of Zhejiang University-SCIENCE