上下文感知推荐系统中基于用户认知行为的偏好获取方法

摘要

To solve the problem that the internal relation between user’s cognitive behaviors and preferences have not been considered which lead to low predictive accuracy in existing recommender systems,inspired by the theory of distributed cognition and the processing model of memory,a cognitive behavior based approach is proposed.Firstly,the paper introduces many cognition concepts into the process of acquiring user preferences under multidimensional context environment, such as cognitive level,cognitive usefulness,cognitive risk,effective cognitive and so on. Secondly,this paper provides the definitions and calculation methods of those concepts.Finally, it elicits user preferences under unidimensional and multidimensional context environments by establishing the cognitive factors’mutual effect model.The authors present empirical experiments by using a real extensive dataset,experimental results show that the proposed algorithms can achieve better prediction accuracy compared with collaborative filtering and context-aware algorithm.%针对现有的偏好获取方法，因未考虑不同用户在各类型上下文环境中的认知行为与用户偏好间的内在联系所导致用户偏好预测准确度不高的问题，受分布式认知理论与记忆信息加工模型启发，提出了一种基于用户认知行为的上下文感知偏好获取方法。在多维上下文环境下，将认知水平、认知有用性、认知风险、有效认知行为等认知领域概念引入偏好获取过程，并分别给出其概念定义及计算方法，通过建立多种认知因素交互影响的偏好获取模型，分别提取在单维与多维上下文环境下的用户偏好。在大规模真实数据集上的实验结果表明，与经典的协同过滤算法及上下文感知算法相比，显著地提高了偏好获取的准确度。