[1]MENG Xiangfu,QI Xueyue,ZHANG Quangui,et al.A POI recommendation approach based on user-POI coupling relationships[J].CAAI Transactions on Intelligent Systems,2021,16(2):228-236.[doi:10.11992/tis.201907034]
Copy
A POI recommendation approach based on user-POI coupling relationships
CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume:
16
Number of periods:
2021 2
Page number:
228-236
Column:
学术论文—机器学习
Public date:
2021-03-05
- Title:
- A POI recommendation approach based on user-POI coupling relationships
- Keywords:
- POI recommendation; K-means; collaborative filtering; coupling relationships; convolutional neural network; location effect; data mining; location-based social network (LBSN); attribute information
- CLC:
- TP311
- DOI:
- 10.11992/tis.201907034
- Abstract:
- In location-based social networks, a hot research topic is the development of methods for making accurate recommendations to users by taking advantage of the coupling relationships between user attributes (or features) and points of interest (POIs). Current POI recommendation approaches mainly leverage the matrix factorization technique based on user ratings of POIs. These approaches routinely confront the problem of rating matrix sparsity, and do not consider the coupling relationships between the respective attributes, such as the descriptive information and comments of users and POIs. In this paper, we propose a POI recommendation framework based on a deep neural network. First, a K-means algorithm is used to cluster POIs by their geographical locations, so that POIs with high location proximity are grouped into one category. Then, a convolutional neural network model is designed to identify the explicit correlations between the respective attributes of users and POIs, for example, the correlation between the age of users and the location of POIs. Another neural network model is designed to simulate the matrix factorization method in machine learning. This model can examine the implicit relationships between users and POIs based on the users’ POI check-in data. Lastly, the explicit and implicit relationships between users and POIs are integrated to comprehensively represent the user-POI coupling relationships. The learned user-POI coupling relationships are input into a fully connected network for recommendation. The proposed model was evaluated on the Yelp data set, and the experimental results show that it achieves high recommendation accuracy.
- References:
-
[1] WANG Weiqing, YIN Hongzhi, CHEN Ling, et al. Geo-SAGE:a geographical sparse additive generative model for spatial item recommendation[C]//Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Sydney, Australia, 2015:1255-1264.
[2] YIN Hongzhi, WANG Weiqing, WANG Hao, et al. Spatial-aware hierarchical collaborative deep learning for POI recommendation[J]. IEEE transactions on knowledge and data engineering, 2017, 29(11):2537-2551.
[3] LI Huayu, GE Yong, HONG Richang, et al. Point-of-Interest recommendations:learning potential check-ins from friends[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco, California, America, 2016:975-984.
[4] HE Xiangnan, LIAO Lizi, ZHANG Hanwang, et al. Neural collaborative filtering[C]//Proceedings of the 26th International Conference on World Wide Web. Perth, Australia, 2017:173-182.
[5] FENG Shanshan, LI Xutao, ZENG Yifeng, et al. Personalized ranking metric embedding for next new POI recommendation[C]//Proceedings of the 24th International Conference on Artificial Intelligence. Buenos Aires, Argentina, 2015:2069-2075.
[6] CHENG Chen, YANG Haiqin, LYU M R, et al. Where you like to go next:successive Point-of-Interest recommendation[C]//Proceedings of the 23th International Joint Conference on Artificial Intelligence. Beijing, China, 2013:2605-2611.
[7] YU Zhiwen, XU Huang, YANG Zhe, et al. Personalized travel package with multi-point-of-interest recommendation based on crowdsourced user footprints[J]. IEEE transactions on human-machine systems, 2016, 46(1):151-158.
[8] LIAO Jianxin, LIU Tongcun, LIU Meilian, et al. Multi-context integrated deep neural network model for next location prediction[J]. IEEE access, 2018, 6:21980-21990.
[9] LONG Yan, ZHAO Pengpeng, SHENG V S, et al. Social personalized ranking embedding for next POI recommendation[C]//Proceedings of the 18th International Conference on Web Information Systems Engineering. Pushchino, Russia, 2017:91-105.
[10] YE Jihang, ZHU Zhe, CHENG Hong. What’s your next move:user activity prediction in location-based social networks[C]//Proceedings of the 2013 SIAM International Conference on Data Mining. Austin, USA, 2013:171-179.
[11] HE Jing, LI Xin, LIAO Lejian, et al. Inferring a personalized next Point-of-Interest recommendation model with latent behavior patterns[C]//Proceedings of the Conference on Artificial Intelligence. Phoenix, America, 2016:137-143.
[12] CUI Qiang, TANG Yuyuan, WU Shu, et al. Distance2Pre:personalized spatial preference for next point-of-interest prediction[M]//YANG Qiang, ZHOU Zhihua, GONG Zhiguo, et al. Advances in Knowledge Discovery and Data Mining. Cham:Springer, 2019:289-301.
[13] LOU Peiliang, ZHAO Guoshuai, QIAN Xueming, et al. Schedule a rich sentimental travel via sentimental POI mining and recommendation[C]//Proceedings of 2016 IEEE Second International Conference on Multimedia Big Data. Taipei, China, 2016:33-40.
[14] ZHANG Chenyi, LIANG Hongwei, WANG Ke, et al. Personalized trip recommendation with POI availability and uncertain traveling time[C]//Proceedings of the 24th ACM International on Conference on Information and Knowledge Management. Melbourne, Australia, 2015:911-920.
[15] LI Huayu, HONG Richang, WU Zhiang, et al. A spatial-temporal probabilistic matrix factorization model for Point-of-Interest recommendation[C]//Proceedings of the 2016 SIAM International Conference on Data Mining. Miami, USA, 2016:117-125.
[16] ZHANG Jiadong, CHOW C Y. GeoSoCa:exploiting geographical, social and categorical correlations for Point-of-Interest recommendations[C]//Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. Santiago, Chile, 2015:443-452.
[17] WANG Xiang, HE Xiangnan, WANG Meng, et al. Neural graph collaborative filtering[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. Paris, France, 2019:165-174.
[18] ZHANG Jiani, SHI Xingjian, ZHAO Shenglin, et al. STAR-GCN:stacked and reconstructed graph convolutional networks for recommender systems[C]//Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence. Macao, China, 2019:4264-4270.
[19] CHENG Chen, YANG Haiqin, KING I, et al. Fused matrix factorization with geographical and social influence in location-based social networks[C]//Proceedings of the 26th AAAI Conference on Artificial Intelligence. Toronto, Canada, 2012:17-23.
[20] LIAN Defu, ZHAO Cong, XIE Xing, et al. GeoMF:joint geographical modeling and matrix factorization for point-of-interest recommendation[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA, 2014:831-840.
[21] XING Shuning, LIU Fangai, ZHAO Xiaohui, et al. Points-of-interest recommendation based on convolution matrix factorization[J]. Applied intelligence, 2018, 48(8):2458-2469.
[22] LIU Ming, DING Yukang, XIA Min, et al. STGAN:a unified selective transfer network for arbitrary image attribute editing[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, America, 2019:3668-3677.
[23] ATHIWARATKUN B, WILSON A, ANANDKUMAR A. Probabilistic FastText for multi-sense word embeddings[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Melbourne, Australia, 2018:1-11.
[24] HORNIK K, STINCHCOMBE M, WHITE H. Multilayer feedforward networks are universal approximators[J]. Neural networks, 1989, 2(5):359-366.
[25] ZHANG Quangui, CAO Longbing, ZHU Chengzhang, at al. CoupledCF:learning explicit and implicit user-item couplings in recommendation for deep collaborative filtering[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence. Stockholm, Sweden, 2018:3662-3668.
[26] MIKOLOV T, CHEN Kai, CORRADO G, et al. Efficient estimation of word representations in vector space[C]//Proceedings of the 1st International Conference on Learning Representations. Scottsdale, USA, 2013:1301-3781.
[27] LIU Yiding, TUAN-ANH P, CONG Gao, et al. An experimental evaluation of Point-of-Interest recommendation in location-based social networks[J]. Proceedings of the VLDB endowment, 2017, 10(10):1010-1021.
[28] RENDLE S, FREUDENTHALER C, GANTNER Z, et al. BPR:Bayesian personalized ranking from implicit feedback[C]//Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence. Montreal, Canada, 2009:452-461.
- Similar References:
Memo
-
Last Update:
2021-04-25