Improved collaborative filtering recommendation based on classification and user trust

被引：0

作者：

Xu X.-L. ^{[1
]}

Xu G.-L. ^{[2
]}

机构：

[1] College of International Vocational Education, Shanghai Second Polytechnic University, Shanghai

[2] College of Mathematics and Information, Shanghai Lixin University of Commerce, Shanghai

来源：

Journal of Electronic Science and Technology | 2016年 / 14卷 / 01期

关键词：

Collaborative filtering; Credibility of ratings; Evaluation on user trust; Item classification; Similarity metric;

D O I：

10.11989/JEST.1674-862X.504071

中图分类号：

学科分类号：

摘要：

When dealing with the ratings from users,traditional collaborative filtering algorithms do notconsider the credibility of rating data, which affects theaccuracy of similarity. To address this issue, the paperproposes an improved algorithm based on classificationand user trust. It firstly classifies all the ratings by thecategories of items. And then, for each category, itevaluates the trustworthy degree of each user on thecategory and imposes the degree on the ratings of theuser. Finally, the algorithm explores the similaritiesbetween users, finds the nearest neighbors, and makesrecommendations within each category. Simulationsshow that the improved algorithm outperforms thetraditional collaborative filtering algorithms andenhances the accuracy of recommendation.

引用

页码：25 / 31

页数：6

共 23 条

[1]

Gao M., Liu K.-C., Wu Z.-F., Personalisation in web computing and informatics: Theories, techniques, applications, and future research, Information Systems Frontiers, 12, 5, pp. 607-629, (2009)

[2]

Yang F., Pan Y.-F., Li J., An adaptive algorithm for collaborative filtering recommendation, Journal of Hebei University of Technology, 39, 3, pp. 82-87, (2010)

[3]

Li C., Liang C.-Y., Dong K., A collaborative filtering recommendation based on item category similarity, Journal of Hefei University of Technology, 31, 3, pp. 360-363, (2008)

[4]

Guo Y.-Q., Huang M.-X., Sun L.-F., A collaborative filtering algorithm of selecting neighbors for each target item, Proc. of the 11th Web Information System and Application Conf. (WISA), pp. 139-143, (2014)

[5]

Choi K., Suh Y., A new similarity function for selecting neighbors for each target item in collaborative filtering, Knowledge-Based Systems, 37, pp. 146-153, (2013)

[6]

Cechinela C., Siciliab M., Sanchez-Alonsob S., Barriocanalb E., Evaluating collaborative filtering recommendations inside large learning object repositories, Information Processing & Management, 49, 1, pp. 34-50, (2013)

[7]

Owen S., Anil R., Dunning T., Friedman E., Mahout in Action, pp. 48-55, (2012)

[8]

Hou C.-Q., Jiao L.-C., Zhang W.-G., Collaborative filtering algorithm via compressing the sparse user-rating-data matrix, Journal of Xidian University, 36, 4, pp. 614-618, (2009)

[9]

Koren Y., Collaborative filtering with temporal dynamics, Communications of the ACM, 53, 4, pp. 89-97, (2010)

[10]

Amatriain X., Lathia N., The wisdom of the few a collaborative filtering approach based on expert opinions from the Web, Proc. of the 32nd Intl. ACM SIGIR Conf. on Research and Development in Information Retrieval, pp. 532-539, (2009)

← 1 2 3 →