Research on User Profiling Technology for Personalized Demands

摘要：

User profiling technology is discussed based on the diversity and randomness of user demands. The key technologies, which include profile initialization and updating, are researched. The user profle is expressed in form of vector space model. Its built using centroid-based classification method. Users browsing behaviors are analyzed to get feedback implicitly, calculating the documents degrees. A periodic adaptive learning mechanism based on Rocchio algorithm is put forward. The profiles capability to dynamic track user needs is verified using satisfaction as evaluation indicator in experiments.

关键词： user profile personalized vector space model Rocchio algorithm

作者: Xu Qi

作者单位: Department of Mechanical Engineering, Taizhou Vocational and Technical College, Zhejiang Taizhou, 318000, China

会议类型: 国际会议

会议名称: 2010 International Conference on Intelligent Computation Technology and Automation(2010 智能计算技术与自动化国际会议 ICICTA 2010)

会议地点: 长沙

会议语种:英文

页码: 2560-2563

在线出版日期: 2010-05-11（万方平台首次上网日期，不代表论文的发表时间）