An Improved Recommendation Method Using Rating and Review Information

Zhang Wei; Huang Jian-hua; Liu Dong-ning; Teng Shao-hua; Liu Zi-ting

doi:10.12052/gdutxb.170014

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

An Improved Recommendation Method Using Rating and Review Information

更新时间：2026-05-27

- An Improved Recommendation Method Using Rating and Review Information
- Vol. 34, Issue 6, Pages: 27-31(2017)
- 作者机构：
  
  1. 广东工业大学计算机学院,广东,广州,510006
  2. 哈尔滨师范大学数学科学学院,黑龙江,哈尔滨,150025
- 作者简介：
- 基金信息：
- DOI：10.12052/gdutxb.170014
  CLC： TP181
- Online First：09 November 2017，
  
  Published：2017
- 稿件说明：
移动端阅览
张巍, 黄健华, 刘冬宁, 滕少华, 刘子婷. 一种改进的结合评分和评论信息的推荐方法[J]. 广东工业大学学报, 2017, 34(6): 27-31.

Zhang Wei, Huang Jian-hua, Liu Dong-ning, et al. An Improved Recommendation Method Using Rating and Review Information[J]. 2017, 34(6): 27-31.
张巍, 黄健华, 刘冬宁, 滕少华, 刘子婷. 一种改进的结合评分和评论信息的推荐方法[J]. 广东工业大学学报, 2017, 34(6): 27-31. DOI： 10.12052/gdutxb.170014.

Zhang Wei, Huang Jian-hua, Liu Dong-ning, et al. An Improved Recommendation Method Using Rating and Review Information[J]. 2017, 34(6): 27-31. DOI： 10.12052/gdutxb.170014.

摘要

随着互联网技术的普及和现代电子商务的迅速发展

推荐系统得到广泛使用

但大多数推荐算法仍存在冷启动、可解释性差两大问题. 本文以结合评分和评论信息的HFT模型为基础

提出了一个改进的HFT模型

通过加入自由向量

捕获原HFT模型中未出现的评论信息

缓解了这两大问题

并进一步提高了模型的准确度. 最后

通过两个大型数据集的实验

结果表明本文的模型准确度优于HFT模型

可为有效利用评论信息资源提供参考.

Abstract

With the Internet technology and modern E-commerce becoming popular

the recommender system has been widely used

but two problems of most recommendation algorithms still remain

i.e. cold start and explanatory problem. Based on the HFT (Hidden Factors and Hidden Topics) model which combines the review and rating information

an improved HFT model is proposed. By adding the free vector in order to capture the review information not discussed in the HFT model

the two problems can be released and the model accuracy improved. At last

the two large datasets shows that the proposed model is better than the HFT model in accuracy

which can largely benefit the use of review information.

关键词

Keywords

references

DU H C, DING L, FENG Y J. Research on business intelligence system with the big data for retail industry [J]. Journal of Guangdong University of Technology, 2014, 31(4): 41-45.

LINDEN G, SMITH B, YORK J. Amazon. com Recommendations: Item-to-Item Collaborative Filtering [J]. IEEE Internet Computing, 2003, 7(1): 76-80.

PAZZANI M J, BILLSUS D. Content-based recommendation systems[M]. Berlin: Springer-Verlag, 2007.

TENG S H, MAI J J, ZHANG W, et al . User multi-faced interests recommendation algorithm based on hybrid similarity [J ] . Journal of Jiangxi Normal University (Natural Science), 2016, 40(5): 481-486.

LI C, LIANG C Y, MA L. A collaborative filtering recommendation algorithm based on domain nearest neighbor [J]. Journal of Computer Research and Development, 2008, 45(9): 1532-1538.

AGGARWAL C C. Model-based collaborative filtering[M]. AGGARWAL C C. Recommender System. Berlin: Springer, 2016.

WANG L, FU X F, WANG X M. Hybrid dynamic collaborative filtering algorithm based on big data sets [J]. Journal of Guangdong University of Technology, 2014, 31(3): 44-48.

SHI Y, LARSON M, HANJALIC A. Reranking collaborative filtering with multiple self-contained modalities[C]//European Conference on Advances in Information Retrieval.[S.I.]: Springer-Verlag, 2011: 699-703

ZHANG W, JIN G Y, TENG L Y, et al . Information recommendation of online social network based on E-CARGO model [J ] . Journal of Chinese Computer Systems, 2015, 36(12): 2662-2666.

MA H, ZHOU D, LIU C, et al. Recommender systems with social regularization[C]//Fourth International Conference on Web Search and Web Data Mining, WSDM 2011, Hong Kong, China:[S.l.]: February. 2011:287-296.

GUNASEKAR S. A survey on using side information in recommendation systems [J]. Nutrition Research Practice, 2012, 9(1): 11-6.

LU J, WU D, MAO M, et al . Recommender syst em application developments [J ] . Decision Support Systems, 2015, 74(C): 12-32.

HWANG R H, HSUEH Y L, CHEN Y T. An effective taxi recommender system based on a spatio-temporal factor analysis model [J]. Information Sciences, 2015, 314(C): 28-40.

WALTER F E, BATTISON S, SCHWEItZER F. A model of a trust-based recommendation system on a social network [J]. Autonomous Agents and Multi-Agent Systems, 2008, 16(1): 57-74.

CAO Y, LI Y. An intelligent fuzzy-based recommendation system for consumer electronic products [J]. Expert Systems with Applications, 2007, 33(1): 230-240.

BERNARDI L, KAMPS J, KISELEVA J, et al . The continuous cold start problem in e-commerce recommender systems [J ] . Computer Science, 2015, 92(2): 28002-28007(6).

MA T, ZHOU J, TANG M, et al . Social network and tag sources based augmenting collaborative recommender system [J ] . Ieice Transactions on Information Systems, 2015, 98(4): 902-910.

LEI X, QIAN X, ZHAO G. Rating prediction based on social sentiment from textual reviews [J]. IEEE Transactions on Multimedia, 2016, 18(9): 1-1.

MCAULEY J, LESKOVEC J. Hidden factors and hidden topics: understanding rating dimensions with review text[C]//ACM Conference on Recommender Systems. Hong Kong: ACM, 2013. 165-172.

KOREN Y, BELL R, VOLINSKY C. Matrix factorization techniques for recommender systems [J]. IEEE, Computer Journal, 2009, 42(8): 30-37.

BLEI D M, NG A Y, JORDAN M I. Latent dirichlet allocation [J]. Journal of Machine Learning Research, 2003, 3(1): 993-1022.

ALAN E G. Gibbs sampling [J]. Journal of the American Statistical Association, 2000, 95(452): 1300-1304.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

The Cross-twin Physics-informed Neural Network for Wave Equations with Conserved Quantities

SCA-YOLO: Real-time Target Detection Based on Deformable Convolution and Context-aware Attention

Multi-Scale Contrastive Embedding Enhanced Adaptive Intrusion Detection Model

Research and Implementation of a Pulsed Laser Ranging Method Based on Digital Mixing

Energy Management Strategy of Hybrid Locomotive Based on Road Condition Parameters

Related Author

No data

Related Institution

No data

AI问答

⁰