融合知识图谱与用户评论的商品推荐算法

doi:10.19678/j.issn.1000-3428.0057570

摘要/Abstract

摘要： 针对基于用户评论的商品推荐算法未充分利用评论之间关联信息的问题，提出一种融合知识图谱与用户评论的商品推荐算法。结合知识图谱对用户评论进行商品特征和情感词提取，构建商品特征集合和商品向量并计算商品相似度矩阵，根据情感词确定商品特征得分，通过随机游走商品节点获取商品特征权重。在此基础上，根据商品特征得分和商品特征权重计算商品推荐价值并进行Top-k推荐。实验结果表明，与基于知识图谱的推荐算法、协同过滤算法、基于内容的推荐算法和混合推荐算法相比，该算法的准确率、召回率和F值最高分别提升15.81%、7.27%和8.55%。

关键词: 推荐算法, 知识图谱, 用户评论, 商品特征, 随机游走模型

Abstract: Focused on the issue that the correlation information between user comments is not fully made use of by the existing comment-based commodity recommendation algorithms,this paper proposes a commodity recommendation algorithm fusing with knowledge graph and user comment.The algorithm uses knowledge graph to extract commodity features and emotional words,the commodity feature set and commodity vector are constructed,and the commodity similarity matrix is calculated.Then the commodity feature score is determined according to emotional words,and the weight of a commodity feature is determined by random walking commodity nodes.On the basis of the score and weight of commodity features,the recommended value of the commodity is calculated and thus Top-k recommendation is made.In the comparison experiments with the knowledge graph-based recommendation algorithm,collaborative filtering recommendation algorithm,content-based recommendation algorithm and hybrid recommendation algorithm,results show that the proposed algorithm increases the precision by up to 15.81%,recall rate by up to 7.27%,and F-score by up to 8.55%.

Key words: recommendation algorithm, knowledge graph, user comment, commodity feature, random walk model

中图分类号:

TP391

汤伟韬, 余敦辉, 魏世伟. 融合知识图谱与用户评论的商品推荐算法[J]. 计算机工程, 2020, 46(8): 93-100.

TANG Weitao, YU Dunhui, WEI Shiwei. Commodity Recommendation Algorithm Fusing with Knowledge Graph and User Comment[J]. Computer Engineering, 2020, 46(8): 93-100.

https://www.ecice06.com/CN/Y2020/V46/I8/93

图/表 9

20200819134919

20200819134922

20200819134925

20200819134928

20200819134931

20200819134934

20200819134937

20200819134940

20200819134943

参考文献

[1] BOBADILLA J,ORTEGA F,HERNANDO A,et al.Recommender systems survey[J].Knowledge-Based Systems,2013,46:109-132.
[2] YU Wei,XU Dehua.Overview and prospect of recommenda-tion algorithm[J].Scientific and Technological and Innova-tion,2019(4):50-52.(in Chinese)俞伟,徐德华.推荐算法概述与展望[J].科技与创新,2019(4):50-52.
[3] XU Zenglin,SHENG Yongpan,HE Lirong,et al.Review on knowledge graph techniques[J].Journal of University of Electronic Science and Technology of China,2016,45(4):589-606.(in Chinese)徐增林,盛泳潘,贺丽荣,等.知识图谱技术综述[J].电子科技大学学报,2016,45(4):589-606.
[4] CHANG Liang,ZHANG Weitao,GU Tianlong,et al.Review of recommendation systems based on knowledge graph[J].CAAI Transactions on Intelligent Systems,2019,14(2):207-216.(in Chinese)常亮,张伟涛,古天龙,等.知识图谱的推荐系统综述[J].智能系统学报,2019,14(2):207-216.
[5] JIANG Mingyang,ZHANG Zhifeng,JIANG Jingiqng,et al.A collaborative filtering recommendation algorithm based on information theory and bi-clustering[J].Neural Computing and Applications,2019,31(12):8279-8287.
[6] JIANG Liaoliang,CHENG Yuting,YANG Lijing,et al.A trust-based collaborative filtering algorithm for E-commerce recommendation system[J].Journal of Ambient Intelligence and Humanized Computing,2019,10(8):3023-3034.
[7] LI Hui,CAI Fei,LIAO Zhifang.Content-based filtering recommendation algorithm using HMM[C]//Proceedings of 2012 International Conference on Computational and Information Sciences.Washington D.C.,USA:IEEE Press,2012:256-263.
[8] WANG Guang,ZHANG Jiemin,DONG Shuaihan,et al.A content-based weighted granularity sequence recommenda-tion algorithm[J].Computer Engineering and Science,2018,40(3):564-570.(in Chinese)王光,张杰民,董帅含,等.基于内容的加权粒度序列推荐算法[J].计算机工程与科学,2018,40(3):564-570.
[9] ZHAO Jiakun,LIU Zhen,CHEN Huimin,et al.Hybrid recommendation algorithms based on ConvMF deep learning model[C]//Proceedings of 2019 International Conference on Wireless Communication,Network and Multimedia Engineering.Washington D.C.,USA:IEEE Press,2019:15-26.
[10] GUO Li,YANG Yijun,HUANG Rong.A hybrid recommendation algorithm based on social and collaborative filtering[C]//Proceedings of 2017 International Con-ference on Measurement,Instrumentation and Automation.Washington D.C.,USA:IEEE Press,2017:25-69.
[11] ZHAO Jing.Research on optimization of personalized product recommendation algorithm based on user reviews[D].Hangzhou:Hangzhou Dianzi University,2019.(in Chinese)赵菁.基于用户评论的个性化产品推荐算法优化研究[D].杭州:杭州电子科技大学,2019.
[12] GUO Wang.The study and application of recommendation algorithm based on user reviews modeling[D].Shanghai:East China Normal University,2019.(in Chinese)郭望.基于用户评论建模的推荐算法研究及应用[D].上海:华东师范大学,2019.
[13] FAN Xuechun.The research and implementation of joint reviews sparse linear recommendation algorithm[D].Xi'an:Northwestern University,2019.(in Chinese)樊雪纯.融合评论的稀疏线性推荐算法研究与实现[D].西安:西北大学,2019.
[14] PENG Yun,WAN Changxuan,JIANG Tengjiao,et al.Extracting product aspects and user opinions based on semantic constrained LDA model[J].Journal of Software,2017,28(3):676-693.(in Chinese)彭云,万常选,江腾蛟,等.基于语义约束LDA的商品特征和情感词提取[J].软件学报,2017,28(3):676-693.
[15] FAN Huilong,QIN Yongbin.Research on text classification based on improved TF-IDF algorithm[C]//Proceedings of 2018 International Conference on Network,Communication,Computer Engineering.Washington D.C.,USA:IEEE Press,2018:259-268.
[16] LIU Qiao,LI Yang,DUAN Hong,et al.Knowledge graph construction techniques[J].Journal of Computer Research and Development,2016,53(3):583-600.(in Chinese)刘峤,李杨,段宏,等.知识图谱构建技术综述[J].计算机研究与发展,2016,53(3):583-600.
[17] CHEBOLU P.PageRank and the random surfer model[EB/OL].[2020-02-25].http://www.math.cmu.edu/~pchebolu/Texfiles/pagerank.pdf.
[18] FANG Chen,ZHANG Hengwei,WANG Na,et al.Personalized service recommendation method based on random walk and diversified graph ranking[J].Acta Electronica Sinica,2018,46(11):2773-2780.(in Chinese)方晨,张恒巍,王娜,等.基于随机游走和多样性图排序的个性化服务推荐方法[J].电子学报,2018,46(11):2773-2780.
[19] BORDES A,USUNIER N,GARCÍADURÁN A,et al.Translating embeddings for modeling multi-relational data[EB/OL].[2020-02-25].https://hal.archives-ouvertes.fr/hal-00920777/document.
[20] MIAO F,QIANG Z,EMLIY C,et al.Transition-based knowledge graph embedding with relational mapping properties[EB/OL].[2020-02-25].http://www.arts.chula.ac.th/~ling/paclic28/program/pdf/328.pdf.
[21] BAGCI H,KARAGOZ P.Context-aware location recom-mendation by using a random walk-based approach[J].Knowledge and Information Systems,2016,47(2):241-260.
[22] ZHU Yuxiao,LÜ Linyuan.Evaluation metrics for recom-mender systems[J].Journal of University of Electronic Science and Technology of China,2012,41(2):163-175.(in Chinese)朱郁筱,吕琳媛.推荐系统评价指标综述[J].电子科技大学学报,2012,41(2):163-175.
[23] GUO Qingyu,ZHUANG Fuzhen,QIN Chuan,et al.A survey on knowledge graph-based recommender systems[EB/OL].[2020-02-25].https://arxiv.org/pdf/2003.00911.pdf.

选择文件类型/文献管理软件名称

选择包含的内容