Please wait a minute...
Data Analysis and Knowledge Discovery
Current Issue | Archive | Adv Search |
The Group recommendation algorithms based on implicit representation learning of multi-attribute ratings
Zhang Chunjin,Guo Shenghui,Ji Shujuan,Yang Wei,Yi Lei
(Network security and Information office, Shandong University of science and technology, Qingdao 266590, China)
(Shandong Provincial Key Laboratory of Wisdom Mine Information Technology, Shandong University of science and technology, Qingdao 266590, China)
Export: BibTeX | EndNote (RIS)      

[Objective] To overcome the serious problem that individual user’s representation learning is affected by the sparsity of individual users’ ratings and improve the accuracy and response speed of recommendation algorithm. [Methods] A neural network-based method is proposed for learning implicit representation from multi-attribute ratings. And then, this method is used to learn the implicit representation of the multi-attribute ratings from two dimensions such as users group and items, respectively. Finally, two group-oriented recommendation algorithms are realized by matching the learned representation of each group and its preference or calculating the attraction of the learned representation of each item to the groups. [Results] Experimental results based on TripAdvisor data set show that : (1) the accuracy and time performances of the two algorithms given in this paper are better than the typical multi-attribute ones and group ones. Moreover, the accuracies of these two algorithms are slightly worse than the personalized one, but the online and offline  running time is reduced by more than 30% and 50% repectively compared to the personalized recommendation algorithm. (2) The recommendation performances about implicit representation learning of users groups slightly outperform the ones about implicit representation learning of items. [Limitations] Due to the difficulty in obtaining real groups data, existing researches generally generate virtual groups based on some kind of clustering algorithm. The same goes for this paper. However, the groups generated by this method is idealized, so group preferences may be more easily aggregated than real group preferences. [Conclusions] Using neural network to learn group users' implicit representation (that is, aggregation of group users' preferences) and items’ implicit representation can effectively improve the recommendation accuracy and the recall by making these two metrics close to the recent personalized ones. At the same time, the online running time is more than 40% lower than the personalized ones.

Key words Group reccommendation algorithms      Rating matrix      Multi-attribute ratings      Implicit representation learning      Nerual network      
Published: 10 October 2020
ZTFLH:  TP393  

Cite this article:

Zhang Chunjin, Guo Shenghui, Ji Shujuan, Yang Wei, Yi Lei . The Group recommendation algorithms based on implicit representation learning of multi-attribute ratings . Data Analysis and Knowledge Discovery, 0, (): 1-.

URL:     OR

[1] Yin Haoran,Cao Jinxuan,Cao Luzhe,Wang Guodong. Identifying Emergency Elements Based on BiGRU-AM Model with Extended Semantic Dimension[J]. 数据分析与知识发现, 2020, 4(9): 91-99.
[2] Qiu Erli,He Hongwei,Yi Chengqi,Li Huiying. Research on Public Policy Support Based on Character-level CNN Technology[J]. 数据分析与知识发现, 2020, 4(7): 28-37.
[3] Wang Sidi,Hu Guangwei,Yang Siyu,Shi Yun. Automatic Transferring Government Website E-Mails Based on Text Classification[J]. 数据分析与知识发现, 2020, 4(6): 51-59.
[4] Liu Weijiang,Wei Hai,Yun Tianhe. Evaluation Model for Customer Credits Based on Convolutional Neural Network[J]. 数据分析与知识发现, 2020, 4(6): 80-90.
[5] Wang Mo,Cui Yunpeng,Chen Li,Li Huan. A Deep Learning-based Method of Argumentative Zoning for Research Articles[J]. 数据分析与知识发现, 2020, 4(6): 60-68.
[6] Yan Chun,Liu Lu. Classifying Non-life Insurance Customers Based on Improved SOM and RFM Models[J]. 数据分析与知识发现, 2020, 4(4): 83-90.
[7] Su Chuandong,Huang Xiaoxi,Wang Rongbo,Chen Zhiqun,Mao Junyu,Zhu Jiaying,Pan Yuhao. Identifying Chinese / English Metaphors with Word Embedding and Recurrent Neural Network[J]. 数据分析与知识发现, 2020, 4(4): 91-99.
[8] Xu Yuemei,Liu Yunwen,Cai Lianqiao. Predicitng Retweets of Government Microblogs with Deep-combined Features[J]. 数据分析与知识发现, 2020, 4(2/3): 18-28.
[9] Xiang Fei,Xie Yaotan. Recognition Model of Patient Reviews Based on Mixed Sampling and Transfer Learning[J]. 数据分析与知识发现, 2020, 4(2/3): 39-47.
[10] Ni Weijian,Guo Haoyu,Liu Tong,Zeng Qingtian. Online Product Recommendation Based on Multi-Head Self-Attention Neural Networks[J]. 数据分析与知识发现, 2020, 4(2/3): 68-77.
[11] Weimin Nie,Yongzhou Chen,Jing Ma. A Text Vector Representation Model Merging Multi-Granularity Information[J]. 数据分析与知识发现, 2019, 3(9): 45-52.
[12] Yunfei Shao,Dongsu Liu. Classifying Short-texts with Class Feature Extension[J]. 数据分析与知识发现, 2019, 3(9): 60-67.
[13] Zhenyu He,Xiangxiang Dong,Qinghua Zhu. Classifying Baidu Encyclopedia Entries with User Behaviors[J]. 数据分析与知识发现, 2019, 3(6): 117-122.
[14] Kan Liu,Lu Chen. Deep Neural Network Learning for Medical Triage[J]. 数据分析与知识发现, 2019, 3(6): 99-108.
[15] Wancheng Chen,Haoran Dai,Yinghan Jin. Appraising Home Prices with HEDONIC Model: Case Study of Seattle, U.S.[J]. 数据分析与知识发现, 2019, 3(5): 19-26.
  Copyright © 2016 Data Analysis and Knowledge Discovery   Tel/Fax:(010)82626611-6626,82624938