计算机应用研究2016，Vol.33Issue(10)：2906-2909,4.DOI:10.3969/j.issn.1001-3695.2016.10.006
融合用户行为和内容的微博用户影响力方法
Microblog user influence algorithm based on user behavior and content
摘要
Abstract
In order to simulate the propagation of information in microblog environment,this paper presented a microblog user influence algorithm based on user behavior(post,follow,forward and comment)and content.Behavior factor data could be ob-tained through the analysis of the behavior of microblog user,and then the user influence weight could be calculated.This algo-rithm established the word co-occurrence matrix using the microblog content,and then used LDA(latent Dirichlet allocation)to identify the potential topic distribution.It applied KL(Kullback Leibler)divergence to obtain the similarity between users,fi-nally acquired the user influence based on using influence weight.Experiments show the effectiveness of this algorithm.关键词
微博/影响力/用户行为/信息传播/LDA模型Key words
microblog/user influence/user behavior/information propagation/latent Dirichlet allocation分类
信息技术与安全科学引用本文复制引用
师亚凯,马慧芳,张迪,鲁小勇..融合用户行为和内容的微博用户影响力方法[J].计算机应用研究,2016,33(10):2906-2909,4.基金项目
国家自然科学基金资助项目（61363058）；甘肃省自然科学研究基金资助项目（145RJZA232，145RJYA259，1606RJYA269）；甘肃省教育厅资助项目（2013B-007，2013A-016）；中国科学院计算技术研究所智能信息处理重点实验室开放基金资助项目（IIP2014-4）；青年教师科研能力提升计划资助项目 （）
