南京大学学报(自然科学版) ›› 2012, Vol. 48 ›› Issue (2): 190197.
郝水龙**,吴共庆,胡学钢
Hao Shui一Long ,Wu Gong一Qing,Hu Xue-Gaug
摘要: 用户兴趣建模是个性化服务的基础与核心,而用户的兴趣会随着时间发生变化,这种用户兴趣漂移现象会导致系统预测用户兴趣的准确性卜降.提出一种基于层次向量空间模型(VSM)的用户兴
趣模型表示及更新处理机制,基于特征项形成兴趣主题,基于兴趣主题形成用户兴趣,由此建立层次型用户兴趣模型.采用基于用户浏览行为来计算用户对网页的兴趣度,快速估计网页兴趣度,以提高个性
化系统的实用性,从而更好地满足用户个性化需求.实验结果表明,设计的用户模型表示及更新机制能有效提高个性化服务性能,准确率及召回率均有所提高.
[1]Ying X M.The research on user modeling for internet personalized services. Ph. D Thesis. Beijing; National University of DefenseTech nology, 2003.(应晓敏.面向 Internet个性化服务的用户建模技术研究.博士论文.北京:国防科学拮术大学,2003). [2]Wu Y H,Chen Y C, Chen A I. P. Enabling personalized recommendation on the web based on user interests and behaviors. Karl A,Ling L. The 11th international Workshop in Research Issues in Data Engineering. Los Alamitos: IEEE CS Press. 2001 .17-24. [3]Zeng C,Xing X C,Zhou L Z. A survey of per- sonalization technology. Journal of Software,2002, 13(10); 1952-1961.(曾春,邢晓春,周立柱.个性化服务技术综述.软件学报,2002,13(10):1952一1961). [4]Lin H F, Yang Y S.The representation and update mechanism for user profile. Journal of Computer Research and Development, 2002,39 (7): 843}-847.(林鸿飞,杨元生.用户兴趣模型的表示和更新机制,计算机研究与发展,2002,39 (7):843一847). [5]Kim H,Chan P K. Learning implicit user inter- est hierarchy for context in personalization. Da- vid L. Proceedings of the 8th international Con- ference on intelligent Uscr interfaces. New York: ACM, 2003,101一108. [6]Mobashcr B, Coolcy R,Srivastave J. Creating adaptive web sites through usage-based cluster ring of URLs. Proceedings of the 1999 IEEE Knowledge and Data Engineering Exchange Workshop, IEEE Computer Society, Washing- ton DC,USA,1999,19一25. [7]Pazzani M,Muramatsu J,Billsus D. Syskill &- Webert:identifying interesting web sites. Mi- chacl P,Jack M. Proceedings of the National Conference on Artificial intelligence,lecture Notes in Computer Science. California; AAAI Press, 1996,54一61. [8]Widmer G, Kubat M. Learning in the presence of concept drift and hidden contexts. Machine Learning, 1996,23(1):69一101. [9]KoychEv I,Schwah I. Adaptation to drifting use`s interests. Ramon L do M. Enric P .Pro- ceedings of European Conference on Machine Learning Workshop; Machine Learning in New information on Age. Lecture Notes in Computer Science. Springer-Verlag, Barcelona, Spain, 2000,39一46. [10]Widyantoro D H,loerger T R,Yen J. Learning user interest dynamics with a thre-descriptor representation. Journal of the Americal Society for Information Science and Technology, 2000,52(3):212一225. [11]oannis P. Colombus; Providing personalized recommendations for drifting user interests. De- partmcnt of Computing Science Faculty of Com- puting Science,Mathematics and Statistics Uni- versity of Glasgow, 2009. [12]Zhao P,Geng H T, Wang Q Y,et al. Re search of a noval automatic personalized alocu- ment recommendation system based on cluste- ring and classification. Journal of Nanjing Uni- versity(Natural Sciences),2006,X2(5):512一 518.(赵鹏,耿焕同,土清毅等.基于聚类和分类的个性化文章自动推荐系统的研究.南京大学学报(自然科学),2006, 42(5);512}-518). [13]Fei H X, Jiang C, Xu L J. User profile based on dendriform vector space model. Computer Technology and Development,2009,19(5): 79-81.费洪晓,蒋种,徐丽娟.基于树状向量空间模型的用户兴趣建模,计算机技术与发展,2009, 19(5): 79-81). [14]Zhang P, Pu J H,LiuY L,et al. A Probabilis tic approach for mining drifting user interest. Ghen G L. Proceedings of the Joint Internation al Conferences on Advances in Data and Web Management. Springer-Verlag, Suzhou,China,2009,381~391 [15]Wu G Q, Wu X D, Hu X G, et al. Web news extraction based on path pattern mining. Pro- ceedings of the 6th international Conference on Fuzzy Systems and Knowledge Discovery,Tian- jin; IEEE Press, 2009,612一617. |
No related articles found! |
|