留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于潜在兴趣语义描述的门户个性化兴趣建模

吴晶 曾骁 陈真勇 熊璋

吴晶, 曾骁, 陈真勇, 等 . 基于潜在兴趣语义描述的门户个性化兴趣建模[J]. 北京航空航天大学学报, 2008, 34(02): 148-152.
引用本文: 吴晶, 曾骁, 陈真勇, 等 . 基于潜在兴趣语义描述的门户个性化兴趣建模[J]. 北京航空航天大学学报, 2008, 34(02): 148-152.
Wu Jing, Zeng Xiao, Chen Zhenyong, et al. Personalized interest modeling on portal based on latent interest semantic description[J]. Journal of Beijing University of Aeronautics and Astronautics, 2008, 34(02): 148-152. (in Chinese)
Citation: Wu Jing, Zeng Xiao, Chen Zhenyong, et al. Personalized interest modeling on portal based on latent interest semantic description[J]. Journal of Beijing University of Aeronautics and Astronautics, 2008, 34(02): 148-152. (in Chinese)

基于潜在兴趣语义描述的门户个性化兴趣建模

基金项目: 国家高技术研究发展计划(863计划)滚动课题资助项目(2002AA113070)
详细信息
  • 中图分类号: TP 301

Personalized interest modeling on portal based on latent interest semantic description

  • 摘要: 日益丰富的门户个性化服务为兴趣建模提出了在描述以及扩展方面更高的要求.提出一种基于潜在兴趣语义描述的门户个性化兴趣模型(PIM-LISD,Personalization Interest Model based on Latent Interest Semantic Description),遵循有限混合模型理论,融入了隐式获取的门户个性化兴趣语义以及潜在兴趣语义关联描述.通过合理选取不同先验分布来适配潜在兴趣语义的后验分布,完善了模型的可解释性和自适应能力,并在建模过程中利用优化的期望最大化(TEM,Tempered Expectation Maximization)算法进行参数估计.实验表明该方法不仅有效节省建模开销,而且能够提升预测精度,从而验证了其正确性和有效性.

     

  • [1] 张卫丰,徐宝文.基于WWW缓冲的用户实时二维兴趣模型[J].计算机学报, 2004,27(4):461-470 Zhang Weifeng, Xu Baowen. WWW cache based model of users’ real time two-dimensions interest[J]. Chinese Journal of Computers, 2004, 27(4): 461-470 (in Chinese) [2] Webb G, Pazzani M, Billsus D. Machine learning for user modeling[J]. User Modeling and User-Adapted Interaction, 2001, 11:19-29 [3] Hofmann T. Collaborative filtering via Gaussian probabilistic latent semantic analysis Proceedings of the ACM Conference on Research and Development in Information Retrieval. Canada:ACM Press, 2003:259-266 [4] Blei D, Ng A, Jordon M. Latent Dirichlet allocation[J]. Journal of Machine Learning Research,2003, 3:993-1022 [5] Marlin B. Modeling user rating profiles for collaborative filtering Proceedings of the 17th Annual Conference on Neural Information Processing Systems. Canada:MIT Press,2003:345-354 [6] McLachlan G J, Peel D. Finite mixture models[M]. New York:Wiley, 2000 [7] Wu Jing, Xiong Zhang. A portal-oriented personalized recomme- ndation using meta-recommender engine Proceedings of 2006 International Conference on Artificial Intelligence.Beijing:BUPT Press, 2006:570-576 [8] Wu Jing, Zhang Pin, Sheng Hao, et al. Mining personalization interest and navigation patterns on portal Proceedings of the 11th Pacific-Asia Conference on Knowledge Discovery and Data Mining, Lecture Notes in Artificial Intelligence. Berlin:Springer-Verlag Heidelberg,2007,4426:948-955 [9] Harper F, Li X, Chen Y, et al. An economic model of user rating in an online recommender system Proceedings of the 10th International Conference on User Modeling, Lecture Notes in Computer Science.Berlin:Springer-Verlag Heidelberg, 2005,3538:307-316
  • 加载中
计量
  • 文章访问数:  2560
  • HTML全文浏览量:  93
  • PDF下载量:  1194
  • 被引次数: 0
出版历程
  • 收稿日期:  2007-03-07
  • 网络出版日期:  2008-02-29

目录

    /

    返回文章
    返回
    常见问答