基于心理学模型的协同过滤推荐方法  

Collaborative Filtering Recommendation Method Based on Psychology Model

作　　者：沈磊[1] 周一民[1] 李舟军[1] 

机构地区：[1]北京航空航天大学计算机学院,北京100191

出　　处：《计算机工程》2010年第20期206-208,216,共4页Computer Engineering

基　　金：国家"973"计划基金资助项目(2007CB310803)

摘　　要：提出一种改进协同过滤推荐的方法。该方法根据心理学中的态度行为关系理论建立用户浏览购买模型,通过分析用户浏览信息,预测用户对项的评分,根据预测的评分,运用协同过滤推荐算法为用户做出推荐。实验验证了用户浏览购买模型的有效性。与传统协同过滤方法进行对比的结果表明,该方法可以有效地改进协同过滤算法的推荐结果。This paper proposes a new approach to improve collaborative filtering recommendation.It applies the attitude-behavior relationship theory in psychology to predict the users’ rating using the Web usage data and adopts the predicted rating in collaborative filtering algorithm to generate recommendations for users.It verifies the prediction model,and compares the method to traditional collaborative filtering algorithm which only records the users’ clicks as their interests.Experimental results demonstrate that the method is more effective at recommending items for users than the traditional algorithm.

关 键 词：协同过滤 推荐系统 态度行为关系 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]