Abstract
With the rapid development of location-based social networks (LBSNs), point-of-interest (POI) recommendations have become a practical problem attracting more and more attention. Recent studies mostly utilize contextual features and sequential patterns of users’ check-ins to recommend POIs. However, there are still many deficiencies in existing works, such as: (1) insufficiently learning relations among far-apart visits in user check-ins; (2) not effectively incorporating geographical information when modeling user-POI interactions; and (3) little exploiting the features from reviews for the POI recommendation task. To tackle the above problems, we propose spatial-temporal and text representation learning (STaTRL), which employs Transformer to learn long-term dependencies among visits in the check-ins sequence and adopts an improved approach to compute the attention between visits by applying geographical information to the self-attention layer in Transformer. Meanwhile, users’ perspectives and POIs’ reputations learned from textual reviews are explored to improve the performance. In addition, a multi-task objective framework is adopted to simultaneously train the hidden representations of users’ historical check-ins trajectories which are shared by these two tasks. Concretely, STaTRL consists of (1) the principal task, i.e., unvisited POI recommendation that recommends to users the unvisited POIs, and (2) the auxiliary task, i.e., user’s POI preference learning whose candidates include both visited and unvisited POIs. We found that the latter task helped train the embedding of visited POIs and further boosted the performance of the former task, and lacking any of both would decline the performance. Extensive experiments on three public datasets demonstrated that STaTRL vastly outperformed the state-of-the-art methods.
Similar content being viewed by others
Notes
We downloaded the authors’ source code provided by their URL.
References
Liu Y, Pham T-AN, Cong G, Yuan Q (2017) An experimental evaluation of point-of-interest recommendation in location-based social networks. In: Proc. of the VLDB Endowment, vol 10, pp 1010–1021
Chen C, Liu Z, Zhao P, Zhou J, Li X (2018) Privacy preserving point-of-interest recommendation using decentralized matrix factorization. In: Proc. of the AAAI Conference on artificial intelligence, vol 32
Rahmani HA, Aliannejadi M, Baratchi M, Crestani F (2020) Joint geographical and temporal modeling base on matrix factorization for point-of-interest recommendation. Advances in Information Retrieval, p 205–219
Zhang Y, Shi Z, Zuo W, Yue L, Liang S, Li X (2020) Joint personalized markov chains with social network embedding for cold-start recommendation. Neurocomputing 386:208–220
Liu S, Wang L (2018) A self-adaptive point-of-interest recommendation algorithm based on a multi-order markov model. Futur Gener Comput Syst 89:506–514
Li G, Chen Q, Zheng B, Yin H, Nguyen QVH, Zhou X (2020) Group-based recurrent neural networks for poi recommendation, ACM/IMS Trans Data Sci 1(1)
Zhao P, Zhu H, Liu Y, Xu J, Li Z, Zhuang F, Sheng VS, Zhou X (2019) Where to go next: A spatio-temporal gated network for next poi recommendation. AAAI, p 5877–5884
Chang B, Park Y, Park D, Kim S, Kang J (2018) Content-aware hierarchical point-of-interest embedding model for successive poi recommendation. IJCAI, p 3301–3307
Wang H, Shen H, Ouyang W, Cheng X (2018) Exploiting poi-specific geographical influence for point-of-interest recommendation. IJCAI, p 3877–3883
Liu W, Wang Z-J, Yao B, Yin J (2019) Geo-alm: Poi recommendation by fusing geographical information and adversarial learning mechanism. IJCAI 7:1807–1813
Yao Z (2018) Exploiting human mobility patterns for point-of-interest recommendation. In: Proc. of the Eleventh ACM International conference on web search and data mining, pp 757–758
Cui Y, Sun H, Zhao Y, Yin H, Zheng K (2021) Sequential-knowledge-aware next poi recommendation: A meta-learning approach. ACM Trans Inf Syst (TOIS) 40(2):1–22
Qian T, Liu B, Viet Q, Nguyen H, Yin H (2019) Spatiotemporal representation learning for translation-based poi recommendation. ACM Trans Inf Syst 37(2):1–24
Lim N, Hooi B, Ng S-K, Wang X, Goh YL, Weng R (2020) Stp-udgat: Spatial-temporal-preference user dimensional graph attention network for next poi recommendation. In: Proc. of the 29TH ACM International Conference on Information and Knowledge Management (CIKM’20), pp 845–855
Gao Q, Trajcevski G, Zhou F, Zhang K, Zhong T, Zhang F (2018) Trajectory-based social circle inference. In: Proc. of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, pp 369–378
Zhou F, Yue X, Trajcevski G, Zhong T, Zhang K (2019) Context-aware variational trajectory encoding and human mobility inference. In: Proc. of World Wide Web Conference, pp 3469–3475
Xing S, Liu F, Wang Q, Zhao X, Li T (2019) Content-aware point-of-interest recommendation based on convolutional neural network. Appl Intell 49(3):858–871
Werneck H, Santos R, Silva N, Pereira Adriano CM, Mourão F, Rocha L (2021) Effective and diverse poi recommendations through complementary diversification models. Expert Syst Appl 175:114775
Han P, Li Z, Liu Y, Zhao P, Li J, Wang H, Shang S (2020) Contextualized point-of-interest recommendation. In: Proc. of the 29th International conference on artificial intelligence, pp 2484–2490
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. Advances in neural information processing systems 30
Mowlaei ME, Abadeh MS, Keshavarz H (2020) Aspect-based sentiment analysis using adaptive aspect-based lexicons. Expert Syst Appl 148:113234
Peng H, Xu L, Bing L, Huang F, Lu W, Si L (2020) Knowing what, how and why: A near complete solution for aspect-based sentiment analysis. In: Proc. of the AAAI Conference on Artificial Intelligence, vol 34, pp 8600–8607
Alqaryouti O, Siyam N, Monem AA, Shaalan K (2020) Aspect-based sentiment analysis using smart government review data. Applied Computing and Informatics
Devlin J, Chang M-W, Lee K, Toutanova K (2018) Bert: Pre-training of deep bidirectional transformers for language understanding, arXiv:1810.04805
Feng S, Tran LV, Cong G, Chen L, Li J, Li F (2020) Hme: A hyperbolic metric embedding approach for next-poi recommendation. In: Proc. of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp 1429–1438
Ho NL, Lim KH (2021) User preferential tour recommendation based on poi-embedding methods. In: Proc. of 26th International conference on intelligent user interfaces, pp 46–48
Zhao S, Zhao T, King I, Lyu MR (2017) Geo-teaser: Geo-temporal sequential embedding rank for point-of-interest recommendation. In: Proc. of the 26th international conference on world wide web companion, pp 153–162
He J, Qi J, Ramamohanarao K (2019) A joint context-aware embedding for trip recommendations. In: Proc. of 2019 IEEE 35th International Conference on Data Engineering (ICDE), IEEE, pp 292–303
Liao J, Liu T, Yin H, Chen T, Wang J, Wang Y (2021) An integrated model based on deep multimodal and rank learning for point-of-interest recommendation. World Wide Web 24(2):631–655
Chen J, Zhang H, He X, Nie L, Liu W, Chua T-S (2017) Attentive collaborative filtering: Multimedia recommendation with item-and component-level attention. In: Proc. of the 40th International ACM SIGIR conference on Research and Development in Information Retrieval, pp 335–344
Manotumruksa J, Macdonald C, Ounis I (2018) A contextual attention recurrent architecture for context-aware venue recommendation. In: Proc. of The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pp 555–564
Zhong T, Zhang S, Zhou F, Zhang K, Trajcevski G, Wu J (2020) Hybrid graph convolutional networks with multi-head attention for location recommendation. World Wide Web 23:3125–3151
Kipf T N, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: Proc. of the 5th International conference on learning representations, pp 1–14
Luo Y, Liu Q, Liu Z (2021) Stan: Spatio-temporal attention network for next location recommendation. In: Proc. of the Web Conference 2021, pp 2177–2185
Ma C, Zhang Y, Wang Q, Liu X (2018) Point-of-interest recommendation: Exploiting self-attentive autoencoders with neighbor-aware influence. In: Proc. of the 27th ACM International Conference on Information and Knowledge Management, pp 697–706
Zuo S, Jiang H, Li Z, Zhao T, Zha H (2020) Transformer hawkes process. In: Proc. of international conference on machine learning, pp 11692–11702
Lai C-H, Hsu C-Y (2021) Rating prediction based on combination of review mining and user preference analysis. Inf Syst 99:101742
Yu D, Mu Y, Jin Y (2017) Rating prediction using review texts with underlying sentiments. Inf Process Lett 117:10–18
Cheng Z, Ding Y, Zhu L, Kankanhalli M (2018) Aspect-aware latent factor model: Rating prediction with ratings and reviews. In: Proc. of the 2018 World Wide Web conference, pp 639–648
Shen R-P, Zhang H-R, Yu H, Min F (2019) Sentiment based matrix factorization with reliability for recommendation. Expert Syst Appl 135:249–258
Karimi A, Rossi L, Prati A (2021) Adversarial training for aspect-based sentiment analysis with bert. 2020 25th International Conference on Pattern Recognition (ICPR), 8797–8803, IEEE
Song Y, Wang J, Liang Z, Liu Z, Jiang T (2020) Utilizing bert intermediate layers for aspect based sentiment analysis and natural language inference, arXiv:2002.04815
Xu H, Shu L, Yu PS, Liu B (2020) Understanding pre-trained bert for aspect-based sentiment analysis, arXiv:2011.00169
Lan Z, Chen M, Goodman S, Gimpel K, Sharma P, Soricut R (2019) Albert: A lite bert for self-supervised learning of language representations, arXiv:1909.11942
Zhang L, Sun Z, Zhang J, Lei Y, Li C, Wu Z, Kloeden H, Klanner F (2020) An interactive multi-task learning framework for next poi recommendation with uncertain check-ins. CAL 301(985):13954
Halder S, Lim KH, Chan J, Zhang X (2021) Transformer-based multi-task learning for queuing time aware next poi recommendation. In: Proc. of Pacific-Asia conference on knowledge discovery and data mining. Springer, pp 510–523
Lian D, Wu Y, Ge Y, Xie X, Chen E (2020) Geography-aware sequential location recommendation. In: Proc. of the 26th ACM SIGKDD International conference on knowledge discovery & data mining, pp 2009–2019
Xia B, Bai Y, Yin J, Li Q, Xu L (2020) Mtpr: A multi-task learning based poi recommendation considering temporal check-ins and geographical locations. Appl Sci 10(19):6664
Cho E, Myers SA, Leskovec J (2011) Friendship and mobility: user movement in location-based social networks. In: Proc. of KDD, ACM, pp 1082–1090
Han P, Li Z, Liu Y, Zhao P, Li J, Wang H, Shang S (2020) Contextualized point-of-interest recommendation. In: Proc. of twenty-ninth international joint conference on artificial intelligence and seventeenth pacific rim international conference on artificial intelligence IJCAI-PRICAI-20
Pontiki M, Galanis D, Pavlopoulos J, Papageorgiou H, Androutsopoulos I, Manandhar S (2014) Semeval-2014 task4: Aspect-based sentiment analysis. In: Proc. of the 8th international workshop on semantic evaluation, pp 27–35
Rahmani H A, Aliannejadi M, Baratchi M, Crestani F (2020) Joint geographical and temporal modeling based on matrix factorization for point-of-interest recommendation. In: Proc. of European conference on information retrieval, pp 205–219
Baratchi M, Afsharchi M, Crestani F (2020) Lglmf: Local geographical based logistic matrix factorization model for poi recommendation. In: Proc. of information retrieval technology, vol 12004, p 66
Beltagy I, Peters ME, Cohan A (2020) Longformer: The long-document transformer, arXiv:2004.05150v2
Kitaev N, Kaiser L, Levskaya A (2020) Reformer: The efficient transformer, arXiv:2001.04451
Lu J, Yao J, Zhang J, Zhu X, Xu H, Gao W, Xu C, Xiang T, Zhang L (2021) Soft: Softmax-free transformer with linear complexity. Advances in Neural Information Processing Systems 34
Xiong Y, Zeng Z, Chakraborty R, Tan M, Fung G, Li Y, Singh V (2021) Nyströmformer: A nystöm-based algorithm for approximating self-attention. AAAI 35(16):14138
Acknowledgements
This work is supported by the Grant-in-aid for JSPS, Grant Number 21K12026, and Suzuki foundation.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
The authors certify that they have NO affiliations with or involvement in any organization or entity with any financial interest (such as honoraria; educational grants; participation in speakers’ bureaus; membership, employment, consultancies, stock ownership, or other equity interest ; and expert testimony or patent-licensing arrangements, or non-financial interest (such as personal or professional relationships, affiliations, knowledge or beliefs) in the subject matter or materials discussed in this manuscript.
Additional information
CRediT authorship contribution statement
Xinfeng Wang: Conception and design, Data collection, Software, Analysis and interpretation of results, Writing- original & editing. Fumiyo Fukumoto: Conception and design, Analysis and interpretation of results, Writing- review draft, Supervision. Jiyi Li: Analysis and interpretation of results, Writing- review draft. Dongjin Yu: Writing- review draft, Supervision. Xiaoxiao Sun: Writing- review draft
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
Wang, X., Fukumoto, F., Li, J. et al. STaTRL: Spatial-temporal and text representation learning for POI recommendation. Appl Intell 53, 8286–8301 (2023). https://doi.org/10.1007/s10489-022-03858-w
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03858-w