一种基于混合粒度的微博用户标签推荐模型  

Recommendation Model of Microblog User Tags Based on Hybrid Grain

作　　者：张瑞[1] 金志刚[1] 王颖[1] 

机构地区：[1]天津大学电子信息工程学院,天津300072

出　　处：《计算机科学》2016年第4期192-196,230,共6页Computer Science

基　　金：国家自然科学基金资助项目(61201179)资助

摘　　要：针对已有的标签推荐模型在实际微博场景运用中存在的多样性、相关性较差等不足,提出了一种基于混合粒度的标签推荐模型。将微博用户的可分析资源分解成由用户信息、标签和微博正文组成的混合粒度,在不同粒度上分别进行个人信息过滤及个性标签分析,从而计算用户标签的熵值与内联度和分类标注标签词汇,提取微博正文主题等,最终为用户推荐具有较强关联性的个性化标签。与一般LDA模型的对比实验证明,该模型可以有效解决新用户的冷启动、标签推荐的准确度等问题,同时保证了推荐的多样性。To avoid the shortcomings of existing tag-recommendation system, we proposed a recommendation model based on hybrid grain. The proposed model divides the resources to multiple grain including user information, tags and blog content. Then filtering personal information, analyzing personality tags, calculating user tag entropy and inline de- gree, classification words, and extracting topic of micro-blog can proceed based on the divided hybrid grain. Through the steps above, the proposed method can recommend associated personalized labels to users. By comparing the experimental results, it shows that the proposed model can efficiently deal with the cold boot problem, improve the accuracy of tag recommendation and insure the diversity of recommended labels.

关 键 词：社会化标签 混合粒度 主题提取 社交网络 多样性 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]