【摘要】 利用用户在特定内容上的行为数据可以近似地推断出用户对于此内容的感兴趣程度或大致评价,我们称为隐式评价。在进行隐式评价计算时,并不是所有的行为数据都是有效数据:某些数据与隐式评价是正/负相关的而有的数据是无关的。将无关数据剔除出去从而获得对于计算隐式评价有用的行为数据集合不但有利于降低计算复杂度并且有利于提高计算精确度。文章通过穷举各种行为数据组合的预测精确度,并对结果进行分析,得出各参数与隐式评价计算的相关性,并得出了对计算隐式评价最有效的行为数据集合。进一步的,文章将上述结果应用到精品课优质资源共享系统中,设计并实现了其中的隐式评价模块。更多还原

【Abstract】 Web usage data have shown that web users exhibit some stable browsing patterns when surfing the Internet and is utilized to determine the users’ preference on specific content or more particularly,to calculate the so called implicit ratings.In this paper,we perform experiments on all the possible combinations of the implicit indicators.After thorough analysis and comparison,4 indicators are chosen as the input of the Artificial Neural Network which is adopted to calculate the implicit ratings.The mechanism of the implicit rating calculation is integrated into an educational resource sharing system as a featured module and worked perfectly.更多还原