计算机科学 ›› 2014, Vol. 41 ›› Issue (1): 69-71.

• 2013 CCF人工智能会议 • 上一篇    下一篇

基于标签和协同过滤的个性化资源推荐

蔡强,韩东梅,李海生,胡耀光,陈谊   

  1. 北京工商大学计算机与信息工程学院 北京100048;北京工商大学计算机与信息工程学院 北京100048;北京工商大学计算机与信息工程学院 北京100048;北京理工大学工业设计研究所 北京100081;北京工商大学计算机与信息工程学院 北京100048
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家自然科学基金项目(71071019),国家高技术研究发展计划(863项目)(2012AA040904),北京市属高等学校人才强教计划资助

Personalized Resource Recommendation Based on Tags and Collaborative Filtering

CAI Qiang,HAN Dong-mei,LI Hai-sheng,HU Yao-guang and CHEN Yi   

  • Online:2018-11-14 Published:2018-11-14

摘要: 传统的协同过滤算法以用户评分体现用户兴趣偏好及资源相似度,忽视了用户、资源自身的特征,并且对稀疏数据和新资源的推荐质量明显下降。在Web2.0时代下,标签可被用户依个人偏好进行自由资源标注。因此,提出了基于标签和协同过滤的推荐算法。其基本思想是将标签作为体现用户兴趣偏好和资源特征的信息,依据用户、标签及资源的多维关系生成用户及资源的标签特征向量,并计算用户对资源的偏好程度和资源相似度,然后基于用户的历史行为预测用户对其他资源的偏好值,最后依据预测偏好值排序产生Top-N推荐结果。通过与传统的协同过滤算法的比较,验证了本算法能有效缓解数据的稀疏性,解决推荐的冷启动问题,提升推荐的准确性,获得更好的推荐效果。

关键词: 标签,协同过滤,推荐算法,用户偏好,资源相似度

Abstract: Traditional collaborative filtering algorithm reflects the user interest preferences and similarity of items by user ratings.It ignores the characteristics of user and project,and performs not very well for sparse data and new items.Under the age of Web2.0,social tab allows the user to label resources based on personal preferences freedom.To solve the problems,a hybrid algorithm based on tags and collaborative filtering recommendation algorithm was proposed.The method uses the label as the user interest information and the item characteristic.Through making use of the multidimensional relationship of the user,social and labeling,algorithm generates user feature vector and Item feature,and calculates the user preferences for items and projects similarity.Then based on the historical behavior of the user,user preference on other projects is predicted.Finally,sorting the predicted preference,recommended results are generated.Experimental results show that our algorithm can effectively alleviate data sparsity,solve the cold start,and enhance the accuracy of the recommendation.

Key words: Tag,Collaborative filtering,Recommendation algorithm,User preference,Item similarity

[1] Kohi A,Ebrahimi S J,Jalali M.Improving the accuracy and efficiency of tag recommendation system by applying hybrid me-thods.comper[C]∥20111st International eConference on Computer and Knowledge Engineering.Mashhad,Iran,2011:242-248
[2] 张斌,张引,高克宁,等.融合关系与内容分析的社会标签推荐[J].软件学报,2012,23(3):476-488
[3] 李聪,梁昌勇,马丽.基于协同过滤与划分聚类的改进推荐算法[J].计算机研究与发展,2008,45(9):1552-1538
[4] 黄创光,印鉴,汪静,等.不确定近邻的协同过滤推荐算法[J].计算机学报,2010,33(8):1369-1377
[5] Koren Y,Bell R,Volinsky C.Matrix Factorization techniques for recommender systems[J].IEEE Computer Society,2009,42(8):30-37
[6] Jin Jian,Chen Qun.A Trust-based top-k recommender systemusing social tagging network[C]∥20129th International Conference on Fuzzy Systems and Knowledge Discovery.China,2012:1270-1274
[7] Nanopoulos A,Rafailidis D,Symeonidis P,et al.MusicBox:personalized music recommendation based on cubic analysis of social tags[J].IEEE Transaction on Audio,Speech,and Language Processing,2010,18(2):407-412
[8] Rau Jer-wei,Huang Jen-wei,Yung Sheng.Improving the qualityof tags using state transition on progressive image search and recommendation system[C]∥2012IEEE International Conference on Systems,Man,and Cybernetics.Seoul,2012:3233-3238
[9] Song Yang,Lu Zhang.Automatic tag recommendation algo-rithms for social recommender systems[J].ACM Transaction on the Web.2011,5(1):1-31
[10] Xia Xiu-feng,Zhang Shu,Li Xiao-ming.A personalized recommendation model based on social tags[C]∥International Workshop on Database Technology and Applications.Wuhan,2010:1-5
[11] 韦素云,业宁,朱健,等.基于资源聚类的全局最近邻的协同过滤算法[J].计算机科学,2012,39(12):149-152
[12] Hao Fei,Zhong Sheng-tong.Tag recommendation based on user interest lattice matching[C]∥IEEE International Conference on Computer Science and Information Technology.Daejeon,2010:276-280
[13] Olvera E P,Godoy D.Valuating term weighting schemes forcontent-based tag recommendation in social tagging systems[J].IEEE Latin America Transaction,2012,10(4):1973-1980

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!