摘要
语义重叠社区发现是社交网络中的一个研究热点,但是现有方法忽略了用户兴趣行为特征和网络拓扑结构特征的有效融合。为此,本文提出了一种用户兴趣偏好优化网络结构的语义重叠社区发现方法。首先利用Word2Vec来提取用户行为的语义信息,并构建用户兴趣偏好模型以对社交网络结构进行优化,再基于用户兴趣偏好改进了传统的PageRank算法,从而用于优选种子节点,最后围绕种子节点进行局部社区发现。在3个真实数据集上检验了本文算法模型的可行性和科学性,通过与多个主流方法的性能对比,结果表明在重叠社区发现中将用户语义属性和网络拓扑属性进行融合,不仅可以优化网络结构,有效缓解买卖流量和僵尸粉等不合理现象,还可以提高语义重叠社区发现的准确率,并有利于进行个性化推荐和避免资源浪费。
Semantic overlapping community detection is a hot research topic in social networks.However,existing meth-ods ignore the effective fusion of user interest behavior features and network topology features.To this end,a semantic over-lapping community detection method is proposed based on user interests to optimize Network structure.Firstly,Word2Vec is used to extract the semantic information of user behavior,and a user interest preference model is constructed to optimize the social network structure.Then,based on user interest preference,the traditional PageRank algorithm is improved to optimize the seed nodes.Finally,local community discovery is carried out around the seed nodes.The feasibility and scientificalness of the algorithm model are tested on three real datasets.By comparing the performance with several mainstream methods,the re-sults show that the fusion of user semantic attributes and network topology attributes in overlapping community discovery can not only optimize the network structure,effectively alleviate unreasonable phenomena such as business traffic and zombie fans,but also improve the accuracy of semantic overlapping community discovery,which is conducive to personalized recom-mendation and avoid resource waste.
作者
杨汕
程树林
郑羽
YANG Shan;CHENG Shuin;ZHENG Yu(School of Computer and Information,Anqing Normal University,Anqing 246133,China;School of Economics and Management,Anqing Normal University,Anqing 246133,China)
出处
《安庆师范大学学报（自然科学版）》
2023年第3期83-88,共6页
Journal of Anqing Normal University(Natural Science Edition)
基金
安徽省自然科学基金项目(2008085MF193)
安徽省优秀青年人才计划项目(gxyqZD2018060)
安徽省教育厅高校自然科学研究项目(KJ2019A0578),安徽省教育厅质量工程项目(2019jyxm0285,2021cyxy047)。
关键词
社交网络
语义重叠社区
兴趣偏好
种子节点
social networks
semantic overlapping communities
interest preference
seed node
