基于主题层次树和语义向量空间模型的用户建模  

Users’ Preference Modeling Based on Topic Hierarchical Tree and Semantic Vector Space Model

作　　者：胡吉明[1] 胡昌平[1] 

机构地区：[1]武汉大学信息资源研究中心

出　　处：《情报学报》2013年第8期838-843,共6页Journal of the China Society for Scientific and Technical Information

基　　金：中国博士后科学基金资助项目(2012M521479);国家自然科学基金(71073119)

摘　　要：语义层次上的用户建模研究对提高用户需求偏好描述准确度和提升推荐服务质量具有重要意义。本文从基于语义层次树的用户建模机理分析人手，将领域本体引入资源描述和用户建模中，通过资源主题特征提取和语义表达、用户需求偏好程度计算，进行基于语义向量空间模型的用户需求偏好建模和表示，最终得到用户的需求偏好模型。实验结果显示，本文所提方法可行且有效，能够提高用户兴趣偏好描述的准确度和提升推荐服务的质量。Users＇ preference modeling is of important significance for the improvement of accuracy of users＇ preference description and service quality. Starting from the mechanism of users＇ modeling based on semantic hierarchical tree, utilizing domain ontology to achieve resources description and users＇ preference modeling, the model and description of users＇ preference based on semantic vector space model were achieved. The process included the extraction of topics＇ characters and semantic representation of resources, and the preference degree computation of users. Subsequently, the users＇ preference model was achieved. Finally, the experiment was implemented to conclude that the methods proposed in this article are feasible and effective, which could improve the accuracy of users＇ preference description and promote the recommendation service quality.

关 键 词：主题层次树 领域本体 语义向量空间模型 用户建模 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]