摘要
个性化网页推荐能高效、便捷地满足用户的信息需求。针对传统个性化技术的不足,提出基于语义的自适应个性化网页推荐方法,采用语义本体和用户兴趣偏移机制构建自适应的语义用户模型,并采用语义质心聚类技术提高推荐的准确率。实验结果表明,与其他推荐方法相比该算法具有更高的推荐准确率和召回率。
Personalized Web page recommendation can satisfy the users' demand for information efficiently and conveniently. In consideration of the deficiencies of the traditional personalized technologies, this paper proposes a self-adaptive personalized Web page recommendation method based on semantics. The method constructs a self-adaptive semantic user model by the use of semantic ontology and user' s interest drifting mechanism, and utilizes the centers of the semantic clusters to improve the precision of recommendation. Experimental results show that the new method has a higher precision and recall compared with the other recommendation method.
出处
《情报理论与实践》
CSSCI
北大核心
2009年第3期93-96,共4页
Information Studies:Theory & Application
基金
国家自然科学基金资助项目
项目编号:60573056
关键词
个性化服务
用户模型
本体
personalized service
user model
ontology