基于协同标记的个性化推荐  

PERSONALIZED INFORMATION SERVICE BASED ON COLLABORATIVE TAGGING

作　　者：徐雁斐[1] 张亮[1] 刘炜[2] 

机构地区：[1]复旦大学计算机与信息技术系,上海200433 [2]上海图书馆,上海200030

出　　处：《计算机应用与软件》2008年第1期9-11,13,共4页Computer Applications and Software

基　　金：973项目(2005CB321905);国家自然科学基金重点项目(69933010)

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。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.

关 键 词：协同标记 个性化推荐 互联网 社会书签 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]