Abstract
Recommender system has attracted increasing attentions of many service providers, as it plays an important role in helping user filter irrelevant information. As an important application in daily life, point-of-interest (POI) recommendation system has become a powerful tool for assisting users make travel decisions, by modeling the impact of external factors on user behavior, such as time, geographical location, to predict future check-ins. However, the influence of intention, an important internal factor, on user check-in behavior has not been well explored. Existing research lacks methods for intention representing learning in POI recommendation, and has not explore the relationship between intention prediction and check-in behavior prediction. Motivated by this, this paper develops a novel sequential-hierarchical attention neural network based recommendation method (SH-Rec), which learns the hierarchy association of intention and sequential dependency of behavior and its interactions to improve user representation in POI recommendation. The main idea of the proposed SH-Rec is to describe user intentions from both hierarchical and sequential aspects using historical check-in sequence and side information, such as POI category attributes. Specifically, we design a novel sequential-hierarchical attention network to model the interaction of hierarchical intention features and sequential behavior features, by stacking several LSTM and self-attention layers. Besides, we model user’s behavior patterns by extracting sequential preference features using memory network. To utilize the contribution of intention learning in recommendation, we propose a weighted optimization function by employing multi-task learning strategy, to migrate knowledge from intention prediction to check-in prediction. Extensive experiments over three real-world datasets evaluate the better performance of the proposed model than the state-of-the-art methods in terms of various evaluation metrics. A series of ablation experiments and parameter experiments verify the better robustness and stability of the proposed model.








Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Data availability
Data can be accessed by request.
References
Gao, Q., Wang, W., Zhang, K., Yang, X., Miao, C., Li, T.: Self-supervised representation learning for trip recommendation. Knowledge-Based Syst. 247, 108791 (2022). https://doi.org/10.1016/j.knosys.2022.108791
Li, H., Wang, X., Zhang, Z., Ma, J., Cui, P., Zhu, W.: Intention-aware Sequential Recommendation with Structured Intent Transition. IEEE Trans. Knowl. Data Eng. 14,(2021). https://doi.org/10.1109/TKDE.2021.3050571
Zhu, G., Wang, Y., Cao, J., Bu, Z., Yang, S., Liang, W., Liu, J.: Neural Attentive Travel package Recommendation via exploiting long-term and short-term behaviors. Knowledge-Based Syst. 211, 106511 (2021). https://doi.org/10.1016/j.knosys.2020.106511
Werneck, H., Silva, N., Pereira, A., Carvalho, M., Bellogín, A., Martinez-Gil, J., Mourão, F., Rocha, L.: A reproducible POI recommendation framework: Works mapping and benchmark evaluation. Inf. Syst. 108, 102019 (2022). https://doi.org/10.1016/j.is.2022.102019
Liu, X., Yang, Y., Xu, Y., Yang, F., Huang, Q., Wang, H.: Real-time POI recommendation via modeling long- and short-term user preferences. Neurocomputing 467, 454–464 (2022). https://doi.org/10.1016/j.neucom.2021.09.056
Lyu, Z., Yang, M., Li, H.: Multi-view group representation learning for location-aware group recommendation. Inf. Sci. (Ny) 580, 495–509 (2021). https://doi.org/10.1016/j.ins.2021.08.086
Islam, M.A., Mohammad, M.M., Sarathi Das, S.S., Ali, M.E.: A survey on deep learning based Point-of-Interest (POI) recommendations. Neurocomputing. 472, 306–325 (2022). https://doi.org/10.1016/j.neucom.2021.05.114
Wang, H., Li, P., Liu, Y., Shao, J.: Towards real-time demand-aware sequential POI recommendation. Inf. Sci. (Ny) 547, 482–497 (2021). https://doi.org/10.1016/j.ins.2020.08.088
Ying, J.J.C., Kuo, W.N., Tseng, V.S., Lu, E.H.C.: Mining user check-in behavior with a random walk for urban point-of-interest recommendations. ACM Trans. Intell. Syst. Technol. (2014). https://doi.org/10.1145/2523068
Yang, K., Yang, Y., Gao, Q., Zhong, T., Wang, Y., Zhou, F.: Self-Explainable Next POI Recommendation. ACM Trans. Recomm. Syst. 2619–2623 (2024). https://doi.org/10.1145/3626772.3657967
Wu, J., Hu, R., Li, D., Ren, L., Hu, W., Xiao, Y.: Where have you been: Dual spatiotemporal-aware user mobility modeling for missing check-in POI identification. Inf. Process. Manag. 59, 103030 (2022). https://doi.org/10.1016/j.ipm.2022.103030
Ni, J., Huang, Z., Hu, Y., Lin, C.: A two-stage embedding model for recommendation with multimodal auxiliary information. Inf. Sci. (Ny) 582, 22–37 (2022). https://doi.org/10.1016/j.ins.2021.09.006
Cui, Z., Zhao, P., Hu, Z., Cai, X., Zhang, W., Chen, J.: An improved matrix factorization based model for many-objective optimization recommendation. Inf. Sci. (Ny) 579, 1–14 (2021). https://doi.org/10.1016/j.ins.2021.07.077
Aliannejadi, M., Rafailidis, D., Crestani, F.: A Joint Two-Phase Time-Sensitive Regularized Collaborative Ranking Model for Point of Interest Recommendation. IEEE Trans. Knowl. Data Eng. (2020). https://doi.org/10.1109/TKDE.2019.2903463
Wang, W., Chen, J., Wang, J., Chen, J., Gong, Z.: Geography-Aware Inductive Matrix Completion for Personalized Point-of-Interest Recommendation in Smart Cities. IEEE Internet Things J. (2020). https://doi.org/10.1109/JIOT.2019.2950418
Sun, K., Qian, T., Chen, X., Zhong, M.: Context-aware seq2seq translation model for sequential recommendation. Inf. Sci. (Ny) 581, 60–72 (2021). https://doi.org/10.1016/j.ins.2021.09.001
Wu, C., Liu, S., Zeng, Z., Chen, M., Alhudhaif, A., Tang, X., Alenezi, F., Alnaim, N., Peng, X.: Knowledge graph-based multi-context-aware recommendation algorithm. Inf. Sci. (Ny) 595, 179–194 (2022). https://doi.org/10.1016/j.ins.2022.02.054
Cai, Z., Yuan, G., Qiao, S., Qu, S., Zhang, Y., Bing, R.: FG-CF: Friends-aware graph collaborative filtering for POI recommendation. Neurocomputing 488, 107–119 (2022). https://doi.org/10.1016/j.neucom.2022.02.070
Yu, D., Yu, T., Wu, Y., Liu, C.: Personalized recommendation of collective points-of-interest with preference and context awareness. Pattern Recognit. Lett. 153, 16–23 (2022). https://doi.org/10.1016/j.patrec.2021.11.018
Rahmani, H.A., Deldjoo, Y., di Noia, T.: The role of context fusion on accuracy, beyond-accuracy, and fairness of point-of-interest recommendation systems. Expert Syst. Appl. 205, 117700 (2022). https://doi.org/10.1016/j.eswa.2022.117700
Tanjim, M. M., Su, C., Benjamin, E., Hu, D., Hong, L., McAuley, J.:. Attentive sequential models of latent intent for next item recommendation. Web Conf. 2020 - Proc. World Wide Web Conf. WWW 2020. 2528–2534 (2020). https://doi.org/10.1145/3366423.3380002
Cabeza-Ramírez, L.J., Sánchez-Cañizares, S.M., Santos-Roldán, L.M., Fuentes-García, F.J.: Impact of the perceived risk in influencers’ product recommendations on their followers’ purchase attitudes and intention. Technol. Forecast. Soc. Change. 184, 121997 (2022). https://doi.org/10.1016/j.techfore.2022.121997
Volokhin, S., Agichtein, E.: Understanding music listening intents during daily activities with implications for contextual music recommendation. CHIIR 2018 - Proc. 2018 Conf. Hum. Inf. Interact. Retr. 2018-March, 313–316 (2018). https://doi.org/10.1145/3176349.3176885
Zhu, N., Cao, J., Liu, Y., Yang, Y., Ying, H., Xiong, H.: Sequential modeling of hierarchical user intention and preference for next-item recommendation. WSDM 2020 - Proc. 13th Int. Conf. Web Search Data Min. 807–815 (2020). https://doi.org/10.1145/3336191.3371840
Ma, G., Wang, Y., Zheng, X., Miao, X., Liang, Q.: A trust-aware latent space mapping approach for cross-domain recommendation. Neurocomputing 431, 100–110 (2021). https://doi.org/10.1016/j.neucom.2020.12.015
Wang, C., Ma, W., Zhang, M., Chen, C., Liu, Y., Ma, S.: Toward Dynamic User Intention: Temporal Evolutionary Effects of Item Relations in Sequential Recommendation. ACM Trans. Inf. Syst. (2021). https://doi.org/10.1145/3432244
Hua, S., Gan, M.: Intention-aware denoising graph neural network for session-based recommendation. Appl. Intell. 53, 23097–23112 (2023). https://doi.org/10.1007/s10489-023-04736-9
Gan, M., Zhang, H.: VIGA: A variational graph autoencoder model to infer user interest representations for recommendation. Inf. Sci. (Ny). 640, 119039 (2023). https://doi.org/10.1016/j.ins.2023.119039
Gan, M., Li, D., Zhang, X.: A disaggregated interest-extraction network for click-through rate prediction. Multimed. Tools Appl. 82, 27771–27793 (2023). https://doi.org/10.1007/s11042-023-14584-x
Chen, C., Song, B., Guo, J., Zhang, T.: Multi-dimensional shared representation learning with graph fusion network for Session-based Recommendation. Inf. Fusion. 92, 205–215 (2023). https://doi.org/10.1016/j.inffus.2022.11.021
Wang, C.: Towards Dynamic User Intention in Sequential Recommendation. WSDM 2021 - Proc. 14th ACM Int. Conf. Web Search Data Min. 1121–1122 (2021). https://doi.org/10.1145/3437963.3441674
Guo, X., Shi, C., Liu, C.: Intention Modeling from Ordered and Unordered Facets for Sequential Recommendation. Web Conf. 2020 - Proc. World Wide Web Conf. WWW 2020. 1127–1137 (2020). https://doi.org/10.1145/3366423.3380190
Xu, Y., Zhu, Y., Yu, J.: Modeling Multiple Coexisting Category-Level Intentions for Next Item Recommendation. ACM Trans. Inf. Syst. (2021). https://doi.org/10.1145/3441642
Meng, X., Lin, X., Wang, X., Zhou, X.: Intention-oriented itinerary recommendation through bridging physical trajectories and online social networks, KSII Trans. Internet Inf. Syst. (2012). https://doi.org/10.3837/tiis.2012.12.010
Zhang, M., Guo, C., Jin, J., Pan, M., Fang, J.: Modeling Hierarchical Intents and Selective Current Interest for Session-Based Recommendation. Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics). 12713 LNAI, 411–422 (2021). https://doi.org/10.1007/978-3-030-75765-6_33
Chen, Y., Liu, Z., Li, J., McAuley, J., Xiong, C.: Intent Contrastive Learning for Sequential Recommendation, WWW 2022 - Proc. ACM Web Conf. 2022, 2172–2182 (2022). https://doi.org/10.1145/3485447.3512090
Chen, W., He, M., Ni, Y., Pan, W., Chen, L., Ming, Z.: Global and Personalized Graphs for Heterogeneous Sequential Recommendation by Learning Behavior Transitions and User Intentions. RecSys 2022 - Proc. 16th ACM Conf. Recomm. Syst. 268–277 (2022). https://doi.org/10.1145/3523227.3546761
Wang, X., Huang, T., Wang, D., Yuan, Y., Liu, Z., He, X., Chua, T.S.: Learning intents behind interactions with knowledge graph for recommendation. Web Conf. 2021 - Proc. World Wide Web Conf. WWW 2021. 878–887 (2021). https://doi.org/10.1145/3442381.3450133
Fan, S., Shi, C., Hu, L., Zhu, J., Ma, B., Han, X., Li, Y.: Metapath-guided heterogeneous graph neural network for intent recommendation. Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min. 2478–2486 (2019). https://doi.org/10.1145/3292500.3330673
Lichman, M., Smyth, P.: Prediction of sparse user-item consumption rates with zero-inflated poisson regression. Web Conf. 2018 - Proc. World Wide Web Conf. WWW 2018. 2, 719–728 (2018). https://doi.org/10.1145/3178876.3186153
Shi, M., Shen, D., Kou, Y., Nie, T., Yu, G.: Attentional Memory Network with Correlation-based Embedding for time-aware POI recommendation. Knowledge-Based Syst. (2021). https://doi.org/10.1016/j.knosys.2021.106747
Zhang, H., Gan, M., Sun, X.: Incorporating Memory-Based Preferences and Point-of-Interest Stickiness into Recommendations in Location-Based Social Networks. ISPRS Int. J. Geo-Information. 10, 36 (2021). https://doi.org/10.3390/ijgi10010036
Zheng, C., Tao, D., Wang, J., Cui, L., Ruan, W., Yu, S.: Memory Augmented Hierarchical Attention Network for Next Point-of-Interest Recommendation. IEEE Trans. Comput. Soc. Syst. (2021). https://doi.org/10.1109/TCSS.2020.3036661
Visa, M., & Patel, D.: Attention based Long-Short Term Memory Model for Product Recommendations with Multiple Timesteps. In 2021 5th International Conference on Computing Methodologies and Communication (ICCMC), pp. 605-612. IEEE, Erode, India (2021). https://doi.org/10.1109/ICCMC51019.2021.9418325.
Liu, W., Lin, Z., Zhu, H., Wang, J., Sangaiah, A.K.: Attention-Based Adaptive Memory Network for Recommendation with Review and Rating. IEEE Access. (2020). https://doi.org/10.1109/ACCESS.2020.2997115
Walker, J., Zhang, F., Zhong, T., Zhou, F., Baagyere, E.Y.: Variational cold-start resistant recommendation. Inf. Sci. (Ny) 605, 267–285 (2022). https://doi.org/10.1016/j.ins.2022.05.025
Gu, X., Zhao, H., Jian, L.: Sequence neural network for recommendation with multi-feature fusion. Expert Syst. Appl. 210, 118459 (2022). https://doi.org/10.1016/j.eswa.2022.118459
Gan, M., Ma, Y.: DeepInteract: Multi-view features interactive learning for sequential recommendation. Expert Syst. Appl. 204, 117305 (2022). https://doi.org/10.1016/j.eswa.2022.117305
Zhang, L., Sun, Z., Zhang, J., Kloeden, H., Klanner, F.: Modeling hierarchical category transition for next POI recommendation with uncertain check-ins. Inf. Sci. (Ny) 515, 169–190 (2020). https://doi.org/10.1016/j.ins.2019.12.006
Huo, Y., Chen, B., Tang, J., Zeng, Y.: Privacy-preserving point-of-interest recommendation based on geographical and social influence. Inf. Sci. (Ny) 543, 202–218 (2021). https://doi.org/10.1016/j.ins.2020.07.046
Funding
This work was supported by the National Natural Science Foundation of China (Nos. 72301182, 72271024, 71871019, 71471016).
This work was supported by the Capital University of Economics and Business Newly Recruited Young Teachers' Research Start-up Fund Project (No. XRZ2023027).
Author information
Authors and Affiliations
Contributions
Yingxue Ma carried out the experiment and result analysis, wrote the main manuscript text, prepared the figures and tables. Mingxin Gan directed the design of experiments. All authors reviewed the manuscript.
Corresponding author
Ethics declarations
Ethical approval
This declaration is “not applicable”.
Competing interests
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Ma, Y., Gan, M. Sequential-hierarchical attention network: Exploring the hierarchical intention feature in POI recommendation. World Wide Web 27, 67 (2024). https://doi.org/10.1007/s11280-024-01295-y
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11280-024-01295-y