融合隐性和显性社交信息的连续兴趣点推荐方法研究
Research on Successive Point-of-Interest Recommendation Model with Explicit and Implicit Social Information

DOI: 10.12677/CSA.2020.1012233, PP. 2212-2226

Keywords: 位置社交网络，连续兴趣点推荐，社交信息，非负矩阵分解，长短时记忆网络
Location-Based Social Network, Successive Point-of-Interest Recommendation, Social Information, Non-Negative Matrix Decomposition, Long Short-Term Memory

Full-Text   Cite this paper   Add to My Lib

Abstract:

利用位置社交网络中的签到数据和用户社交关系开展对连续兴趣点推荐问题的研究。本文利用非负矩阵分解技术，构建用户的社交信息模型，考虑用户隐性和显性社交关系，将社交网络图转化为低维特征向量；改进LSTM结构，提出融合社交信息的连续兴趣点推荐模型SLSTM，该模型共享非负矩阵分解技术训练的图顶点向量，实现了图结构数据和签到序列数据的有效融合。在Gowalla和BrightKite签到数据集上进行实验，结果表明SLSTM模型优于目前主流的连续兴趣点推荐算法。在Gowalla数据集上，SLSTM模型在Recall@10指标的性能较SERM模型提高了17%，在BrightKite数据集上，Recall@10指标提高了15.2%，说明SLSTM模型在连续兴趣点推荐中的有效性。基于位置的社交网络包含丰富的上下文信息，本文只着重考虑了社交信息对推荐结果的影响。用户隐性社交关系对用户的行为偏好有重要影响；融合隐性和显性社交信息的连续兴趣点推荐方法具有较好的推荐结果。
This paper uses the check-in data and the user’s social relationship in the location based social networks (LBSN) to carry out the research on the successive point-of-interests recommendation. Firstly, this paper uses the non-negative matrix decomposition technique to model users’ implicit and explicit social information and transform the social network graph into a low-dimensional fea-ture vector. Secondly, by improving the LSTM model, this paper proposes a successive point-of-interest recommendation SLSTM that merges social information, which shares the graph vertex vector trained by the non-negative matrix decomposition technique and realizes the effective fusion of graph structure data and check-in sequence data. The experimental results show that the SLSTM model improves the performance of the Recall@10 metric by 17% and 15.2% over the SERM model on the Gowalla and BrightKite dataset respectively. Location-based social networks contain rich contextual information. This paper only focuses on the impact of social information on recommendation results. The implicit social relationships have an important influence on their behavioral preferences in location-based social networks. Successive point-of-interest recommenda-tion model with explicit and implicit social information performs better than other recommendation algorithms.

References

[1]	Rendle, S., Freudenthaler, C., Schmidtthieme, L., et al. (2010) Factorizing Personalized Markov Chains for Next-Basket Recommendation. The Web Conference, Raleigh, 26-30 April 2010, 811-820. https://doi.org/10.1145/1772690.1772773
[2]	Rendle, S., Freudenthaler, C., Gantner, Z., et al. (2009) BPR: Bayesian Personalized Ranking from Implicit Feedback. Conference on Uncertainty in Artificial Intelligence, Montreal, 18-21 June 2009, 452-461.
[3]	Yao, D., Zhang, C., Huang, J., et al. (2017) SERM: A Recurrent Model for Next Loca-tion Prediction in Semantic Trajectories. Conference on Information and Knowledge Management, California, 14-19 Oc-tober 2017, 2411-2414. https://doi.org/10.1145/3132847.3133056
[4]	胡德敏, 杨晨. 一种基于多类型情景信息的兴趣点推荐模型[J]. 计算机应用研究, 2018, 35(6): 1636-1640, 1675.
[5]	苏畅, 武鹏飞, 谢显中. 基于用户兴趣和地理因素的兴趣点推荐方法[J]. 计算机科学, 2019, 46(4): 228-234.
[6]	Zhang, W. and Wang, J. (2015) Location and Time Aware Social Collaborative Retrieval for New Suc-cessive Point-of-Interest Recommendation. Conference on Information and Knowledge Management, Guilin, 20-23, November 2015, 1221-1230. https://doi.org/10.1145/2806416.2806564
[7]	Cheng, C., Yang, H., Lyu, M.R., et al. (2013) Where You Like to Go Next: Successive Point-of-Interest Recommendation. International Joint Conference on Artificial Intelligence, Beijing, 3-9 August 2013, 2605-2611.
[8]	He, J., Li, X., Liao, L., et al. (2016) Inferring a Per-sonalized Next Point-of-Interest Recommendation Model with Latent Behavior Patterns. National Conference on Artifi-cial Intelligence, Phoenix, 12-17 February 2016, 137-143.
[9]	Liu, S. and Wang, L. (2018) A Self-Adaptive Point-of-Interest Recommendation Algorithm Based on a Multi-Order Markov Model. Future Generation Computer Systems, 89, 506-514. https://doi.org/10.1016/j.future.2018.07.008
[10]	Liu, X., Liu, Y. and Li, X. (2016) Explor-ing the Context of Locations for Personalized Location Recommendations. Proceedings of the International Joint Con-ference on Artificial Intelligence, New York, 7-15 July 2016, 1188-1194..
[11]	Zhao, S., Zhao, T., Yang, H., et al. (2016) Stellar: Spatial-Temporal Latent Ranking for Successive Point-of-Interest Recommendation. Proceedings of the National Conference on Artificial Intelligence, Phoenix, 12-17 February 2016, 315-321.
[12]	Liu, Q., Wu, S., Wang, L., et al. (2016) Predicting the Next Location: A Recurrent Model with Spatial and Temporal Contexts. Thirtieth AAAI Con-ference on Artificial Intelligence, Phoenix, 12-17 February 2016, 194-200.
[13]	Zhao, P., Zhu, H., Liu, Y., et al. (2018) Where to Go Next: A Spatio-Temporal LSTM Model for Next POI Recommendation.
[14]	Li, R., Shen, Y., Zhu, Y., et al. (2018) Next Point-of-Interest Recommendation with Temporal and Multi-Level Context Attention. International Con-ference on Data Mining, Singapore, 17-20 November 2018, 1110-1115. https://doi.org/10.1109/ICDM.2018.00144
[15]	Cho, K., Van, B., Bahdanau, D., et al. (2014) On the Properties of Neural Machine Translation: Encoder-Decoder Approaches. Proceedings of SSST-8, Eighth Workshop on Syntax, Se-mantics and Structure in Statistical Translation, Doha, October 2014, 103-111. https://doi.org/10.3115/v1/W14-4012
[16]	Liu, Y., Pham, T.N., Cong, G., et al. (2017) An Experimental Evalua-tion of Point-of-Interest Recommendation in Location-Based Social Networks. Proceedings of the VLDB Endowment, 10, 1010-1021. https://doi.org/10.14778/3115404.3115407
[17]	Bao, J., Zheng, Y., Wilkie, D., et al. (2015) Recommendations in Location-Based Social Networks: A Survey. Geoinformatica, 19, 525-565. https://doi.org/10.1007/s10707-014-0220-8
[18]	Huang, L., Ma, Y., Liu, Y., et al. (2015) Point-of-Interest Rec-ommendation in Location-Based Social Networks with Personalized Geo-Social Influence. China Communications, 12, 21-31. https://doi.org/10.1109/CC.2015.7385525
[19]	Li, H., Ge, Y., Hong, R., et al. (2016) Point-of-Interest Recommendations: Learning Potential Check-Ins from Friends. Knowledge Discovery and Data Mining, San Francisco, 24-27 August 2016, 975-984. https://doi.org/10.1145/2939672.2939767
[20]	Zhang, D., Li, M., Wang, C., et al. (2016) Point of Interest Rec-ommendation with Social and Geographical Influence. International Conference on Big Data, Washington DC, 5-8 De-cember 2016, 1070-1075. https://doi.org/10.1109/BigData.2016.7840709
[21]	李鑫, 刘贵全, 李琳, 等. LBSN上基于兴趣圈中社会关系挖掘的推荐算法[J]. 计算机研究与发展, 2017, 54(2): 394-404.
[22]	Gao, R., Li, J., Li, X., et al. (2018) A Personal-ized Point-of-Interest Recommendation Model via Fusion of Geo-Social Information. Neurocomputing, 273, 159-170. https://doi.org/10.1016/j.neucom.2017.08.020
[23]	温彦, 马立健, 曾庆田, 等. 基于地理信息偏好修正和社交关系偏好隐式分析的POI推荐[J]. 数据分析与知识发现, 2019, 3(8): 30-40.
[24]	Lee, D.D. and Seung, H. (1999) Learning the Parts of Objects by Non-Negative Matrix Factorization. Nature, 401, 788-791. https://doi.org/10.1038/44565
[25]	Lecun, Y., Bengio, Y., Hinton, G.E., et al. (2015) Deep Learning. Nature, 521, 436-444. https://doi.org/10.1038/nature14539
[26]	Hochreiter, S. and Schmidhuber, J. (1997) Long Short-Term Memory. Neural Computation, 9, 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
[27]	Kingma, D.P. and Ba, J. (2014) Adam: A Method for Stochastic Optimization. Proceedings of the 3rd International Conference on Learning Representations (ICLR), Alberta, 14-16 April 2014, 1-14.
[28]	Huang, L., Ma, Y., Wang, S., et al. (2019) An Attention-Based Spatiotemporal LSTM Network for Next POI Recommendation. IEEE Transactions on Services Computing, 1-11. https://doi.org/10.1109/TSC.2019.2918310
[29]	Xie, M., Yin, H., Wang, H., et al. (2016) Learning Graph-Based POI Embedding for Location-Based Recommendation. Conference on Information and Knowledge Management, Indi-anapolis, 24-28 October 2016, 15-24. https://doi.org/10.1145/2983323.2983711
[30]	Li, Y., Luo, Y., Zhang, Z., et al. (2019) Context-Aware Atten-tion-Based Data Augmentation for POI Recommendation. International Conference on Data Engineering, Macao, 8-12 April 2019, 177-184. https://doi.org/10.1109/ICDEW.2019.00-14

Full-Text