一种基于语义推理的网络社区发现模型  

Semantic Link Based Cyber Community Discovery Model

作　　者：任薇[1] 阮淇昱 韩孟凯 邱玉辉[2] REN Wei;RUAN Yuqi;HAN Mengkai;QIU Yuhui(School of Computer and Information Science,Southwest University,Chongqing 400715,China;School of Artificial Intelligence,Southwest University,Chongqing 400715,China)

机构地区：[1]西南大学计算机与信息科学学院软件学院,重庆400715 [2]西南大学人工智能学院,重庆400715

出　　处：《西南大学学报（自然科学版）》2022年第9期178-186,共9页Journal of Southwest University(Natural Science Edition)

基　　金：国家自然科学基金项目(62003280).

摘　　要：网络社区作为新的资源发布和共享方式,其形成模式、发现方式等是网络发展研究热点之一.由于聚类的随机性以及现有划分算法对个体和链接属性信息的语义利用不充分,社会网络的社区不能得到准确的分类.本文提出基于语义推理的网络社区发现模型,通过节点关系的拓扑结构和节点间的语义联系,抽取多层语义进行搜索并进行社区发现.在ego-Facebook数据集上的实验结果表明,当社区大小增长到1000以后,本算法更加稳定,更适用于节点包含丰富的语义且结构稀疏的网络.As a new way of publishing and sharing resources,the network community is one of the hot spots in the research of network growth.Due to the randomness of clustering and the insufficient semantic utilization of individual node as well as link attributes by existing partitioning algorithms,communities in social networks cannot achieve satisfied classifications.This paper proposed a network community discovery model based on semantic reasoning,which extracts multi-layer semantics through the topology of network and the semantic connections between nodes.Experiment results on the ego-Facebook dataset show that the algorithm is more stable and more suitable for networks with rich semantics and sparse structure when the community size grows to more than 1000.

关 键 词：社区发现 语义网络 语义链 多层模型 知识图谱 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]