Show simple item record

dc.contributor.authorWang, Jingjinzh_CN
dc.contributor.authorLin, Kunhuizh_CN
dc.contributor.authorLi, Jiazh_CN
dc.contributor.author林坤辉zh_CN
dc.date.accessioned2015-07-22T02:16:12Z
dc.date.available2015-07-22T02:16:12Z
dc.date.issued2013zh_CN
dc.identifier.citationProceedings of the 8th International Conference on Computer Science and Education, ICCSE 2013, 2013:1473-1476zh_CN
dc.identifier.other20133416637798zh_CN
dc.identifier.urihttps://dspace.xmu.edu.cn/handle/2288/85752
dc.descriptionConference Name:8th International Conference on Computer Science and Education, ICCSE 2013. Conference Address: Colombo, Sri lanka. Time:August 26, 2013 - August 28, 2013.zh_CN
dc.description.abstractRecommendation system has been widely used in electronic commerce, news, web2.0, E-learning and other fields. Collaborative filtering is one of the most important algorithms. But as scale of recommendation system continues to expand, more and more problems appear. Data sparsity and poor prediction are main problems that recommendation system has to face. To improve the quality and performance, a new collaborative filtering recommendation algorithm combining user-clustering and Slope One algorithm is proposed. In our algorithm, users were clustered into several classes based on users' rating on items; therefore the useless information was filtered. Then the slope-one scheme was applied to predict the object rating. The experiments were applied to the MovieLens dataset to exploit the benefits of our detector and the experiment results show that the accuracy of our algorithm is in advance of previous research. ? 2013 IEEE.zh_CN
dc.language.isoen_USzh_CN
dc.publisherIEEE Computer Societyzh_CN
dc.source.urihttp://dx.doi.org/10.1109/ICCSE.2013.6554158zh_CN
dc.subjectCollaborative filteringzh_CN
dc.subjectComputer sciencezh_CN
dc.subjectData processingzh_CN
dc.subjectE-learningzh_CN
dc.subjectEducation computingzh_CN
dc.subjectEngineering educationzh_CN
dc.subjectExperimentszh_CN
dc.subjectRecommender systemszh_CN
dc.titleA collaborative filtering recommendation algorithm based on user clustering and Slope One schemezh_CN
dc.typeConferencezh_CN


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record