【摘要】 互联网上社会书签的应用日渐流行,并由此诞生了协同标记。它提供了一种便捷有效的组织管理海量信息的方式。为了充分发挥其潜能,需要提取出协同标记中的深层关系。提出了发掘这些关系进而构造用户个人元数据,并据此进行个性化推荐的方法。提出的推荐算法同时具有基于内容和基于协同过滤推荐方法的优点,且可以灵活满足用户长短期的多个兴趣。在著名社会书签网站del.icio.us上的数据进行的实验显示了方法的优越性。更多还原

【Abstract】 Social bookmarking becomes popular recently,and therefore collaborative tagging emerges.It is considered as a brand-new information infrastructure on the web.To achieve its potential,it is needed to extract substantial correlation among tags provided by users.A technique to distill the crucial points of a user’s personal metadata is proposed.Based on the extracted information,a profile of a user’s interest is maintained from his personal tags,and personalized recommendation is made according to it.The proposed approach equilibrates both strength of content-based and collaborative recommendation,and satisfies all users’ requirements from short-term to long-term.Experiments against data from the famous social bookmarking website del.icio.us reveal the superiority of the method.更多还原