计算机科学 ›› 2016, Vol. 43 ›› Issue (9): 266-268.doi: 10.11896/j.issn.1002-137X.2016.09.053

• 人工智能 • 上一篇    下一篇

一种基于贝叶斯网络的个性化协同过滤推荐方法研究

付永平,邱玉辉   

  1. 安康学院电子与信息工程学院 安康725000,西南大学计算机与信息科学学院 重庆400715
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受国家自然科学基金:基于情感语义的全局均衡智能调度理论与方法研究(61152003)资助

Method of Personalized Collaboration Filter Recommendation Based on Bayesian Network

FU Yong-ping and QIU Yu-hui   

  • Online:2018-12-01 Published:2018-12-01

摘要: 针对推荐系统不能有效进行个性化推荐问题,在协同过滤过程中引入语义校验,通过对基于用户的协同过滤推荐结果进行语义校验,剔除概率较低的推荐结果,选择概率较高的结果推荐给用户,从而实现个性化语义推荐。在构建贝叶斯语义校验网络时,增加用户“喜好”偏好字段,通过问卷调查及信息反馈,确定用户对物品的喜好偏好值,确保贝叶斯语义校验网络的科学性。实验结果表明,本方法能剔除用户喜好度较低的物品,提高用户的满意度。

关键词: 协同过滤,贝叶斯网络,推荐系统,语义

Abstract: Lacking of high efficiency personal recommendation in recommendation system,we proposed a new method in collaboration filtering recommendation system by using semantic checking.We check the result of collaboration filtering based on user item by Bayesian semantic to eliminate the item of lower probability,and to select the higher probability item to users.In constructing the Bayesian semantic check network,we add an emotion field named “fancy” by questionnaire survey and information feedback,and we decide user’s emotion for some goods to ensure the scientific of semantic checking network.Experiments show that the method can eliminate the items with low user preferences and improve the satisfaction degree of the users.

Key words: Collaboration filtering,Bayesian network,Recommendation system,Semantic

[1] Liao S,Zou T,Chang H.An Association Rules and Sequential Rules Based Recommendation System[C]∥4th International Conference on Wireless Communications,Networking and Mobile Computing.IEEE,2008:1-4
[2] Forsati R,Meybodi M,Rahbar R.An efficient algorithm for web recommendation systems[C]∥IEEE/ACS International Confe-rence on Computer Systems and Applications.2009:579-586
[3] Hu J.Application and research of collaborative filtering in e-commerce recommendation system[C]∥2010 3rd International Conference on Computer Science and Information Technology (ICCSIT).2010:686-689
[4] Kim D H,Im I,Atlur V.A clickstream-based collaborative filtering recommendation model for e-commerce[C]∥ IEEE International Conference on E-Commence.2005:84-91
[5] Massa P,Avesani P.Trust-aware collaborative filtering for re-commender systems[C]∥Proceedings of International Confe-rence on Cooperative Information Systems.Agia Napa,Cyprus:2004:492-508
[6] Kim J,Jeong D,Baik D K.Ontology-based semantic recommen-dation system in home network environment[J].IEEE Transactions on Consumer Electronics,2009,55(3):1178-1184
[7] Gao Qi,Yan Jun-wei,Liu Min.A Semantic Approach to Recommendation System Based on User Ontology and Spreading Activation Model[C]∥International Conference on Network and Parallel Computing.2008:488-492
[8] Feng Gou-he,Huang Jia-xing.Research on Collaborative Filte-ring Book Recommendation Based on Hadoop and Mahout[J].Library and Information Work,2013,57(18):116-121(in Chinese) 奉国和,黄家兴.基于Hadoop 与Mahout的确协同过滤图书推荐研究[J].图书情报工作,2013,57(18):116-121
[9] Han Feng-xia, Sun Yan-chao.Research on Personalized bookRecommendation System Based on Collaborative Filtering Algorithm [J].Digital Library,2015(4):99-102(in Chinese) 韩凤霞,孙彦超.基于协同过滤算法的个性化图书推荐系统的研究[J].数字图书馆,2015(4):99-102
[10] Wu jian-wei,Yu xiao-hong,Chen wen-qing.Density-based Dynamic Collaborative Filtering Books Recommendation Algorithm[J].Application Research of Computers,2010,27(8):3013-3015(in Chinese) 武建伟,俞晓红,陈文清.基于密度的动态协同过滤图书推荐算法[J].计算机应用研究,2010,27(8):3013-3015
[11] Liu J.A Personalized Information Filtering Method Based onSimple Bayesian Classifier[M]∥Advances in Electronic Commerce,Web Application and Communication.Springer Berlin Heidelbreg,2012
[12] Tewarii A S,Kumar A,Barman A G,et al.Book Recommendation System Based on Combine Features of Content Based Filtering,Collaborative Filtering and Association Rule Mining[C]∥IEEE International Advance Computing Conference.2014:500-503

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!