面向个性化服务的用户兴趣偏移检测及处理方法

被引:5
作者
杨杰
陈恩红
机构
[1] 中国科学技术大学计算机科学与技术学院
关键词
个性化系统; 兴趣偏移; 兴趣模型; 概念偏移;
D O I
暂无
中图分类号
TP319 [专用应用软件];
学科分类号
摘要
个性化服务系统的目标是根据不同用户的兴趣喜好为不同用户提供针对性服务,其核心是建立关于用户兴趣的描述,即用户兴趣建模。然而,现实生活中用户兴趣常常发生不可预测的变化,兴趣偏移问题一直困扰着建模技术,阻碍个性化服务系统性能的进一步提高。为了寻找切实可行的方法解决兴趣偏移问题,本文针对用户兴趣建模的兴趣偏移问题进行系统的研究,着重分析了兴趣偏移的检测方法和处理机制,对时间窗口、遗忘模型、长短期模型等隐式调整方法以及主要显式检测方法和技术进行了系统评述,并在此基础上提出了针对兴趣偏移问题的进一步研究方向。
引用
收藏
页码:72 / 76+63 +63
页数:6
相关论文
共 10 条
  • [1] Learning implicit user interest hierarchy for context in personalization
    Kim, Hyoung-Rae
    Chan, Philip K.
    [J]. APPLIED INTELLIGENCE, 2008, 28 (02) : 153 - 166
  • [2] SIGIR 2003 workshop report[J] . Susan Dumais,Thorsten Joachims,Krishna Bharat,Andreas Weigend.ACM SIGIR Forum . 2003 (2)
  • [3] An adaptive recommendation system without explicit acquisition of user relevance feedback
    Shahabi, C
    Chen, YS
    [J]. DISTRIBUTED AND PARALLEL DATABASES, 2003, 14 (02) : 173 - 192
  • [4] Machine Learning for User Modeling[J] . Geoffrey I. Webb,Michael J. Pazzani,Daniel Billsus.User Modeling and User-Adapted Interaction . 2001 (1)
  • [5] Selecting examples for partial memory learning
    Maloof, MA
    Michalski, RS
    [J]. MACHINE LEARNING, 2000, 41 (01) : 27 - 52
  • [6] Identifying and tracking changing interests
    Crabtree I.B.
    Soltysiak S.J.
    [J]. International Journal on Digital Libraries, 1998, 2 (1) : 38 - 53
  • [7] Learning in the presence of concept drift and hidden contexts
    Widmer, G
    Kubat, M
    [J]. MACHINE LEARNING, 1996, 23 (01) : 69 - 101
  • [8] EXPERIENCE WITH A LEARNING PERSONAL ASSISTANT
    MITCHELL, T
    CARUANA, R
    FREITAG, D
    MCDERMOTT, J
    ZABOWSKI, D
    [J]. COMMUNICATIONS OF THE ACM, 1994, 37 (07) : 81 - 91
  • [9] Gradual forgetting for adaptation to concept drift .2 I. Koychev. Proceedings of ECAI 2000 Workshop Current Issues in Spatio-Temporal Reasoning . 2000
  • [10] Lecture Notes in Computer Science[C]. The First International Conference on Web-Age Information Management,1600