基于区域交互模型的SNS网络用户影响力评估  

Study on user influence analysis via regional user interaction model in online social networks

作　　者：王楠[1] 孙钦东[1] 周亚东[2] 王汉秦 隋连升[1] 

机构地区：[1]西安理工大学网络计算与安全技术陕西省重点实验室,陕西西安710048 [2]西安交通大学智能网络与网络安全教育部重点实验室,陕西西安710049

出　　处：《通信学报》2016年第1期160-169,共10页Journal on Communications

基　　金：国家自然科学基金资助项目(No.61172124;No.61571360;No.61202392)~~

摘　　要：针对现有方法与模型未能准确体现不同距离用户之间真实交互行为的问题,提出了一种基于用户区域交互模型的用户影响力评估方法。区域交互模型利用影响力传递的不同方式,刻画不同距离之间用户的交互行为模式,能更为真实准确地反映在线社会网络用户之间的交互行为。通过计算用户对相邻用户的显性影响力与非相邻用户的隐性影响力,可有效识别在线社会网络中大影响力用户、僵尸粉用户等不同类型用户。基于新浪微博与人人网真实数据开展用户影响力评估以及相应的用户角色识别实验,结果显示,与现有方法相比,基于区域交互模型的识别方法可以准确有效地识别出在线社会网络中的大影响力用户、僵尸粉用户等各类型用户。Conventional user influence researches do not accurately reflect the real interaction pattern between different users in online social networks. In order to solve this problem, a user influence evaluation method based on regional user interaction model has been proposed. The regional user interaction model can illustrate the real online social network user interaction pattern between users with different distance by the influence transfer effect. The method calculates the direct influence and the indirect influence of each user in online social networks and identifies the influential users and zombie users. Experiments are based on the real data of Sina Weibo and Ren Ren online social networks and the results show that compared with the existing methods the method has better accuracy and efficiency for the influential user and zombie user identification.

关 键 词：用户影响力评估 区域交互模型 在线社会网络 大影响力用户 僵尸粉 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]