Integrating Spatial Relationship into a Matrix Factorization Model for POI Recommendation

被引：0
|
作者：
Wei H. [1 ,2 ]
Li K. [1 ,2 ]
He X. [1 ,2 ]
Tian Z. [1 ,2 ]
机构：
[1] School of Geo-Science and Technology, Zhengzhou University, Zhengzhou
[2] Joint Laboratory of Eco-Meteorology, Zhengzhou University, Chinese Academy of Meteorological Sciences, Zhengzhou
来源：
Wuhan Daxue Xuebao (Xinxi Kexue Ban)/Geomatics and Information Science of Wuhan University | 2021年 / 46卷 / 05期
关键词：
Location-based social network(LBSN); Matrix factorization; Point of interest (POI) recommendation; Space distance; Spatial relationship;
D O I：
10.13203/j.whugis20200355
中图分类号：
学科分类号：
摘要：
Objectives: Point of interest (POI) recommendation is the prevalent personal service in location-based social network(LBSN), and aims to provide personalized recommendation services by using the information carried by LBSN. The utilization of spatial relationship information as the side information supplies a chance to product better POI recommend. However, thousands of users and POIs in the LBSN make the user-POI check-in matrix very large and sparse. In addition, check-in record data is typical implicit feedback data, which cannot directly reflect the user's preference. To tackle the aforementioned challenges, we propose a relational matrix factorization model based on cooperative competition matrix factorization (CC-MF). Methods: The CC-MF model can simulate the relationship between users and POIs, and divides spatial relationships into spatial distance relationship and spatial topological relationship. In order to alleviate the problem of data sparsity, the model excavates the spatial relationships among POIs, POIs and users by integrating spatial relationships. Firstly, we use nonlinear function to establish the spatial distance relationship between users and POIs, which can connect the relationship between users and POIs. Then, k-nearest neighbor (kNN) algorithm is used to calculate the geo-neighbors of POI by considering the spatial distance factor of spatial topological relationship, which can further alleviate the sparsity of data. Finally, the spatial relationship is integrated into the matrix factorization model. Meanwhile, the weighted least square method is used as the objective function of the CC-MF model to relieve the implicit feedback problem. Experiments are carried out on the real-world check-in Foursquare datasets. We test the recommendation performance of the proposed model and baseline methods, and analyze the crucial influence of different spatial relationships on POI recommendation. The precision and recall are used as evaluation metrics. Results: The results show that: (1) The CC-MF model significantly improves the precision and recall of the recommendation results. (2) Considering the spatial distance factor of the spatial topological relationship can further improve the performance of the recommendation system. Conclusions: Therefore, CC-MF model can make use of spatial relationship better and more comprehensive. The proposed CC-MF model has better scalability and better interpretability, and can alleviate the problems of data sparsity and implicit feedback usage. © 2021, Editorial Board of Geomatics and Information Science of Wuhan University. All right reserved.
引用
下载
收藏
页码：681 / 690
页数：9
相关论文
共 38 条
  • [1] Bobadilla J, Ortega F, Hernando A, Et al., Recommender Systems Survey, Knowledge-Based Systems, 46, pp. 109-132, (2013)
  • [2] Lu J, Wu D, Mao M, Et al., Recommender System Application Developments: A Survey, Decision Support Systems, 74, pp. 12-32, (2015)
  • [3] Zhang C, Wang K., POI Recommendation Through Cross-Region Collaborative Filtering, Knowle-dge and Information Systems, 46, 2, pp. 369-387, (2016)
  • [4] Cai L, Xu J, Liu J, Et al., Integrating Spatial and Temporal Contexts into a Factorization Model for POI Recommendation, International Journal of Geographical Information Science, 32, 3, pp. 524-546, (2018)
  • [5] Ning Jinsheng, Wu Xuequn, Liu Ziyao, Multi-user Location Recommendation Considering Road Accessibility and Time-Cost, Geomatics and Information Science of Wuhan University, 44, 5, pp. 633-639, (2019)
  • [6] Zhu Jinghua, Ming Qian, POI Recommendation by Incorporating Trust-Distrust Relationship in LBSN, Journal on Communications, 39, 7, pp. 157-165, (2018)
  • [7] Liao Guoqiong, Jiang Shan, Zhou Zhiheng, Et al., Double Fine-Granularity POI Recommendation on Location-Based Social Networks, Journal of Computer Research and Development, 54, 11, pp. 2600-2610, (2017)
  • [8] Baral R, Li T., Exploiting the Roles of Aspects in Personalized POI Recommender Systems, Data Mining and Knowledge Discovery, 32, 2, pp. 320-343, (2018)
  • [9] Wang Yandong, Li Hao, Wang Teng, Et al., The Mining and Analysis of Emergency Information in Sudden Events Based on Social Media, Geomatics and Information Science of Wuhan University, 41, 3, pp. 290-297, (2016)
  • [10] Yu Wenhao, Ai Tinghua, Yang Min, Et al., Detecting "Hot Spots" of Facility POIs Based on Kernel Density Estimation and Spatial Autocorrelation Technique, Geomatics and Information Science of Wuhan University, 41, 2, pp. 221-227, (2016)
1234