摘要
针对现有微博社区发现的准确性与效用性问题,提出了一种高效的基于用户内容相似度的微博社区发现算法。首先对微博用户兴趣模型进行分析,进而挖掘微博意见领袖,通过AP算法对意见领袖进行兴趣聚类,以聚类结果为社区中心结合模块度优化算法完成微博社区发现。经实验验证了该方法可以更好地发现微博社区结构。
The community found in micro-blog has important research significance in personalized recommendation, micro-blog marketing, public opinion monitoring and so on. In view of the accuracy and utility of the existing micro-blog community, an efficient micro-blog community discovery algorithm based on user content similarity was proposed. This paper first analyzed the user interest model of micro-blog, and then excavated micro-blog opinion leaders, and finally clustered the interest groups of opinion leaders by AP algorithm. The results were taken as community center to combine with modularity optimization algorithm to complete micro-blog community discovery. This method can better find the structure of the micro-blog community.
作者
王高飞
张月琴
陈健
WANG Gaofei;ZHANG Yueqin;CHEN Jian(College of Information and Computer Science,Taiyuan University of Technology,Taiyuan 030024,China)
出处
《太原理工大学学报》
CAS
北大核心
2019年第3期374-379,共6页
Journal of Taiyuan University of Technology
基金
山西省应用基础研究项目(201701D121057)
关键词
微博
社区发现
意见领袖
AP算法
模块度优化算法
microblog
community discovery
opinion leader
AP algorithm
Modular degree optimization algorithm
