摘要
协同过滤算法的用户评分与用户偏好之间可能存在偏差,导致推荐准确度降低。为此,提出一种基于归因理论的用户偏好提取算法。基于用户行为的一致性、区别性和正负偏好信息提取用户偏好。融合偏好相似性与评分相似性以获得更优的最近邻集合,计算用户对未评分项目的预测评分值。在通用数据集Movies Lens-1M上进行实验,结果表明,在10%偏好相似性与60%评分相似性的融合条件下,该算法的推荐准确度取得最优值,且优于传统协同过滤算法以及HU-FCF、BM/CPT-V等改进算法。
The possible deviations between user ratings and user preferences in collaborative filtering algorithms result in reduced recommendation accuracy.For this problem,a user preference extraction algorithm based on attribution theory is proposed.User preferences are extracted based on the consensus,distinctiveness,positive and negative preference information of user behaviors.Merge preference similarity and rating similarity to get a better nearest neighbor set,and calculate a user's predicted rating for unrated items.Experiments are carried on Movies Lens-1 M dataset and the results show that under the merging condition of 10% preference similarity and 60% rating similarity,the algorithm achieves the highest recommendation accuracy,which is better than the traditional collaborative filtering algorithm and other improved algorithms,such as HU-FCF、BM/CPT-V.
引文
[1] LU Jie,WU Dianshuang,MAO Mingsong,et al.Recommender system application developments:a survey[J].Information Systems,2015,74(4):12-32.
[2] GOLDBERG D,NICHOLS D,OKI B M,et al.Use collaborative filtering to weave an information tapestry[J].Communications of the ACM,1992,35(12):61-70.
[3] SON L H.Dealing with the new user cold-start problem in recommender systems:a comparative review[J].Information Systems,2016,58(5):87-104.
[4] GODOY-LORITE A,GUIMERA R,MOORE C,et al.Accurate andscalable social recommendation using mixed-membership stochastic block models[J].Proceedings of the National Academy of Sciences,2016,113(50):14207-14212.
[5] SON L H.HU-FCF:a hybrid user-based fuzzy collaborative filtering method in recommender system[J].Expert Systems with Applications,2014,41(5):6861-6870.
[6] JOSHI B,IUTZELER F,AMINI M R.Asynchronous distributed matrix factorization with similar user and item based regularization[C]//Proceedings of ACM Conference on Recommender Systems.New York,USA:ACM Press,2016:75-78.
[7] KIM Y D,CHOI S.Bayesian binomial mixture model for collaborative prediction with non-random missing data[C]//Proceedings of ACM Conference on Recommender Systems.New York,USA:ACM Press,2014:201-208.
[8] HOFMANN T.Latent semantic models for collaborative filtering[J].ACM Transactions on Information Systems,2004,22(1):89-115.
[9] KELLEY H H.Attribution theory in social psychology[J].Nebraska Symposium on Motivation,1967,15(6):192-238.
[10] Shams B,HARATIZADEH S.TasteMiner:mining partial tastes for neighbor-based collaborative filtering[J].Journal of Intelligent Information Systems,2017,48(1):165-189.
[11] 贾伟洋,李书琴,李昕宇,等.基于离散量和用户兴趣贴近度的协同过滤推荐算法[J].计算机工程,2018,44 (1):226-232,237.
[12] ZOU Caifeng,ZHANG Daqiang,WAN Jiafu,et al.Using concept lattice for personalized recommendation system design[J].IEEE Systems Journal,2017,11(1):305-314.
[13] PATRA B K,LAUNONEN R,OLLIKAINEN V,et al.A new similarity measure using Bhattacharyya coefficient for collaborative filtering in sparse data[J].Knowledge-Based Systems,2015,82(7):163-177.
[14] SARWAR B,KARYPIS G,KONSTAN J,et al.Item-based collaborative filtering recommendation algorithms[C]//Proceedings of the 10th International Conference on World Wide Web.New York,USA:ACM Press,2001:285-295.
[15] HARPER F M,KONSTAN J A.The movie lens datasets:history and context[EB/OL].[2018-01-01].http://files.grouplens.org/papers/harper-tiis2015.pdf.