一种兴趣驱动的跨网络传播优化算法  

AN INTEREST-DRIVEN PROPAGATION OPTIMIZATION ALGORITHM ACROSS NETWORKS

作　　者：李雷[1] 邓诗琦 赵博 施化吉[1] 施磊磊[1] Li Lei;Deng Shiqi;Zhao Bo;Shi Huaji;Shi Leilei(Computer Science and Communication Engineering,Jiangsu University,Zhenjiang 212013,Jiangsu,China;School of Journalism,Communication University of China,Beijing 100024,China)

机构地区：[1]江苏大学计算机科学与通信工程学院,江苏镇江212013 [2]中国传媒大学新闻传播学部新闻学院,北京100024

出　　处：《计算机应用与软件》2021年第7期222-231,280,共11页Computer Applications and Software

基　　金：国家自然科学基金项目(61806086);江苏省普通高校研究生科研创新计划项目(CXZZ13_0689)。

摘　　要：现有社交网络影响力优化算法难以发现跨多个社交网络的全局影响力最大节点。对此,利用用户兴趣和跨网络重叠用户对多个社交网络进行研究,提出一种兴趣驱动的跨网络传播模型,设计跨网络影响力的优化算法。实验结果表明,相比现有算法,该算法仅用1/5的种子节点就能达到相同的影响力效果,同时计算时间开销减少了6/7。Existing influence maximization algorithms are difficult to find out the most influential nodes across networks.In this paper,the IMaN problem is studied based on user interest and overlapping users across networks.An interest-driven influence propagation model across networks(ID-IPM)and an optimization algorithm for influence maximization across networks(OA-IPaN)are proposed.The test results show that compared with the existing algorithm,the optimization algorithm can achieve the same influence range with 1/5 seed nodes,and reduce the computing time by 6/7.

关 键 词：社交网络 用户兴趣 影响力最大化 跨网络 信息传播 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]