考虑时序性和动态信任的工程经验知识推荐技术

被引：2

作者：

黄颖

蒋祖华

刘璞凌

王海丽

机构：

[1] 上海交通大学机械与动力工程学院

来源：

上海交通大学学报 | 2016年 / 50卷 / 09期

关键词：

知识推荐; 工程经验知识; 动态信任; MediaWiki平台;

D O I：

10.16183/j.cnki.jsjtu.2016.09.013

中图分类号：

TP391.3 [检索机];

学科分类号：

081203 ; 0835 ;

摘要：

随着用户和词条数量的增长,"用户-词条"评分矩阵变得极其稀疏,导致基于相似度计算的推荐算法精度降低.提出一种基于用户短期兴趣时序性变化的评分矩阵进行预填充.由于MediaWiki社区用户群之间的信任呈动态变化,定义了追随率反映同一时间窗内具有相似兴趣的用户对知识推荐的参考性.最后设计实验,确定时间窗长度T的最优参数,通过比较CFBDT(Collaborative filtering based on dynarnic trust)算法与3类现有算法的效果,验证其可行性.

引用

页码：1422 / 1429

页数：8

共 16 条

[1]

Collaborative filtering with the simple Bayesian classifier. MIYAHARA K,PAZZANI M J. Proceedings of the 6th Pacific Rim International Conference on Artificial Intelligence . 2000

[2]

Self-organizing collaborative filtering in global-scale massive multi-user virtual environments. HOHFELD A,GRATZ P,BECK A,et al. Proceedings of the 2009 ACM Symposium on Applied Computing . 2009

[3]

Slope one predictors for online rating-based collaborative filtering. Daniel Lemire,Anna Maclachlan. Proceedings of the 2005 SIAM International Conference on Data Mining . 2005

[4] An empirical study of a cross-level association rule mining approach to cold-start recommendations [J].

Leung, Cane Wing-ki ;

Chan, Stephen Chi-fai ;

Chung, Fu-lai .

KNOWLEDGE-BASED SYSTEMS, 2008, 21 (07) :515-529

[5]

Latent Class Models for Collaborative Filtering. Hofmann,T.,Puzicha,J. International Joint Conference on Artificial Intelligence . 1999

[6]

Collaborative filtering with temporal dynamics. Koren Y. Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining . 2009

[7]

From SocialNetworks to Behavioral Networks in Recommender Systems. Esslimani,I,Brun,A,Boyer,A. Proceedings of International the 2009 Conference on Advancesin Social Network Analysis and Mining (ASONAM’’ 09) . 2009

[8] 基于高斯pLSA模型与项目的协同过滤混合推荐 [J].

陈登科 ;

孔繁胜 .

计算机工程与应用, 2010, 46 (23) :209-211+234

[9]

RECON:A reciprocal recommender for online dating. PIZZATO L A,REJ T,ChUNG T,et al. Proceeding of the 4th ACM Conference on Recommendation System . 2010

[10] Time Weight Update Model Based on the Memory Principle in Collaborative Filtering [J].

Li, Dan ;

Cao, Peng ;

Guo, Yucui ;

Lei, Min .

JOURNAL OF COMPUTERS, 2013, 8 (11) :2763-2767

← 1 2 →