Rating prediction model based on heterogeneous network representation learning

被引：0
|
作者：
Zhan N. [1 ,2 ]
Liu W. [3 ]
Chen X. [4 ]
Pu J. [1 ,2 ]
机构：
[1] Research Institute of Beihang University in Shenzhen, Shenzhen
[2] School of Computer Science and Engineering, Beihang University, Beijing
[3] School of Economics and Management, Beihang University, Beijing
[4] China North Vehicle Research Institute, Beijing
来源：
Liu, Wei (wayne@buaa.edu.cn) | 1600年 / Beijing University of Aeronautics and Astronautics (BUAA)卷 / 47期
关键词：
Neural network; Random walk; Rating prediction; Recommendation system; Representation learning;
D O I：
10.13700/j.bh.1001-5965.2020.0100
中图分类号：
TP39 [计算机的应用];
学科分类号：
081203 ; 0835 ;
摘要：
In recent years, it has become a hot spot to deeply analyze the personalized data of e-commerce users and provide recommendation services.The basis of recommendation service is to mine the potential interest of users and predict user's interest of products. Therefore, this paper takes this as the background to study the user's rating prediction of products. This paper studies the application of relational data of e-commerce in recommendation system, and puts forward a method of rating prediction by using network representation learning. First, the relational data is constructed into a heterogeneous network, and the users and items are the nodes in the network. Then, a personalized heterogeneous network sampling method is designed, which takes into account the network structure information and the similarity between nodes, and the nodes are represented and learned. Finally, the learned user and items representation vectors are input into the neural network for training, and the optimized neural network model is used to predict the score. The experimental results show that this method has high accuracy on YELP 13, Movielens 100k and Movielens 1m datasets. Compared with common methods, the accuracy is improved by more than 6.5%. © 2021, Editorial Board of JBUAA. All right reserved.
引用
收藏
页码：1077 / 1084
页数：7
相关论文
共 21 条
  • [1] LI G, ZHANG Z, WANG L, Et al., One-class collaborative filtering based on rating prediction and ranking prediction, Knowledge-Based Systems, 124, pp. 46-54, (2017)
  • [2] MARGARIS D, VASILOPOULOS D, VASSILAKIS C, Et al., Improving collaborative filtering's rating prediction coverage in sparse datasets through the introduction of virtual near neighbors, 2019 10th International Conference on Information, Intelligence, Systems and Applications(IISA), pp. 1-8, (2019)
  • [3] LIU H, HU Z, MIAN A, Et al., A new user similarity model to improve the accuracy of collaborative filtering, Knowledge-Based Systems, 56, pp. 156-166, (2014)
  • [4] GANU G, ELHADAD N, MARIAN A., Beyond the stars: Improving rating predictions using review text content, International Workshop on the Web and Databases, pp. 1-6, (2009)
  • [5] FIKIR O B, YAZ I O, OZYER T., Movie rating prediction with matrix factorization algorithm, pp. 631-643, (2013)
  • [6] YANG Y, XIANG Y, XIONG L., Collaborative filtering and recommendation algorithm based on matrix factorization and user nearest neighbor model, Journal of Computer Applications, 32, 2, pp. 395-398, (2012)
  • [7] CHAMBUA J, NIU Z, YOUSIF A, Et al., Tensor factorization method based on review text semantic similarity for rating prediction, Expert Systems with Applications, 114, pp. 629-638, (2018)
  • [8] KOREN Y, BELL R, VOLINSKY C., Matrix factorization techniques for recommender systems, Computer, 42, 8, pp. 30-37, (2009)
  • [9] VIARD T, FOURNIER-S'NIEHOTTA R., Movie rating prediction using content-based and link stream features
  • [10] QIAO Z, ZHANG P, HE J, Et al., Combining geographical information of users and content of items for accurate rating prediction, Proceedings of the Companion Publication of the 23rd International Conference on World Wide Web Companion, pp. 361-362, (2014)
123