Effect of rating residual on recommendation quality
-
摘要: 从理论上分析了评分偏差对于推荐质量的影响;基于潜在偏好及已知评分对评分偏差进行度量,其中潜在偏好通过心理测量学模型计算得出;通过设定不同的评分偏差水平,对评分偏差的影响进行了实验验证.理论分析及实验验证表明:评分偏差可导致推荐准确度及覆盖度下降;基于高质量的评分数据,协同过滤算法可为用户作出好的推荐.Abstract: The effect of the rating residual on recommendation quality was analyzed. The rating residual was measured through user ratings and latent preferences. Latent preferences were computed with psychometric models. With different levels of rating residual, the effect of the rating residual was experimentally evaluated on real world datasets. Theoretical analysis and experimental results show that rating residual has negative effects on recommendation accuracy and coverage. Based on high quality of data, collaborative filtering algorithms can make precise recommendations for users.
-
[1] Gediminas A,Alexander T.Toward the next generation of recommender systems:a survey of the state-of-the-art and possible extensions[J].IEEE Trans on Knowledge and Data Engineering(TKDE),2005,17(6):734-749 [2] Badrul S,George K,Joseph K,et al.Item-based collaborative filtering recommendation algorithms //Proc of 10th International World Wide Web Conference(WWW-01).New York:ACM Press,2001:285-295 [3] O-Mahony M P,Hurley N J,Silvestre G C M.Detecting noise in recommender system databases //Proc of the 10th International Conference on Intelligent User Interfaces(IUI -06).New York:ACM Press,2006:109-115 [4] Cao Huanhuan,Chen Enhong,Yang Jie,et al.Enhancing recommender systems under volatile user interest drifts //Proc of the 18th ACM Conference on Information and Knowledge Management (CIKM-09).New York:ACM Press,2009:1257-1266 [5] Xavier A,Neal L,Pujol J M,et al.The wisdom of the few:a collaborative filtering approach based on expert opinions from the web //Proc of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR-09).New York:ACM Press,2009:532-539 [6] Herlocker J L,Konstan J A,Terveen L G,et al.Evaluating collaborative filtering recommender systems[J].Transactions on Information Systems (TOIS),2004,22(1):5-53 [7] Wang Jun,de Vries A P,Reinders M J T.Unifying user-based and item-based collaborative filtering approaches by similarity fusion //Proc of the 29th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR-06).New York:ACM Press,2006:501-508 [8] 杜文久.高等项目反应理论[M].重庆:西南师范大学出版社,2007:71-88 Du Wenjiu.Advanced item response theory[M].Chongqing:Southwest Normal University Press,2007:71-88(in Chinese) [9] Cheng Yunghsiang.Exploring passenger anxiety associated with train travel[J].Transportation,2010,37(6):875-896 [10] David Andrich.A rating formulation for ordered response categories[J].Psychometrikia,1978,43(4):561-573 [11] Hu Biyun,Li Zhoujun,Wang Jun.User-s latent interest-based collaborative filtering //Proc 32nd European Conference on Information Retrieval(ECIR-10).Berlin:Springer-Verlag,2010:619-622 [12] Hu Biyun,Li Zhoujun,Chao Wenhan,et al.User preference representation based on psychometric models //Proc 22nd Australia Database Conference (ADC-11).Sydney:ACS,2011:57-64 [13] Linacre Mike.WINSTEPS Rasch measurement computer program.Chicago:Winsteps.com,2007.http://www.winsteps.com [14] Linacre Mike.PROX for polytomous data[J].Rasch Measurement Transactions,1995,8(4):400 [15] Wright B D,Masters G N.Rating scale analysis[M].Chicago:MESA Press,1982:100
点击查看大图
计量
- 文章访问数: 2472
- HTML全文浏览量: 180
- PDF下载量: 766
- 被引次数: 0