基于NVPA算法的社交网络影响力最大化算法  

Social Network Influence Maximization Algorithm based on NVPA Algorithm

作　　者：徐浩 潘理[2] XU Hao;PAN Li(School of Electronic Information and Electrical Engineering,Shanghai Jiaotong University,Shanghai 200240,China;Shanghai Key Laboratory of Integrated Administration Technologies for Information Security,Shanghai 200240,China)

机构地区：[1]上海交通大学电子信息与电气工程学院,上海200240 [2]上海市信息安全综合管理技术研究重点实验室,上海200240

出　　处：《通信技术》2018年第4期924-929,共6页Communications Technology

基　　金：国家自然科学基金"面向网络舆情监管的目标群体行为特征检测与分析技术"(No.U1636105)~~

摘　　要：衡量与评估用户影响力是在线社交网络分析中的一个经典问题。现有的相关研究主要从个体角度出发,利用贪婪算法进行影响力分析,很少考虑网络中用户一般都会形成社区这样一个客观事实,而一般个体角度的影响力最大化算法都存在运行效率低的问题。因此,提出了一种基于社区的影响力最大化算法NVPA-IM(Neighborhood Vector Propagation Algorithm Influence Maximization)。通过与经典影响力最大化算法的对比分析,证明了所提算法在保证算法精度的同时,显著提高了算法效率。Measuring and evaluating user influence is a classic issue in online social network analysis.The existing related research mainly uses greedy algorithm to analyze the influence from individual perspective,and seldom considers the fact that users in the network generally form the community.However,in general,the algorithm of maximizing influence based on individual perspectives has the problem of low operational efficiency.Therefore,a community-based influence maximization algorithm NVPA-IM(Neighborhood Vector Propagation Algorithm Influence Maximization)is proposed.Through comparison with the classical maximization algorithm,it is proved that the proposed algorithm can improve the algorithm efficiency while ensuring the accuracy of the algorithm.

关 键 词：社交网络 社区发现 节点影响力评估 影响力最大化 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]