融合用户自身因素与互动行为的微博用户影响力计算方法

Method of Weibo User Influence Calculation Integrating Users’ Own Factors and Interaction Behavior

由于微博高影响力用户在商品营销、社会舆论引导等方面起着重要的作用,因此挖掘高影响力用户成为了微博社交网络中的热点研究问题。针对微博用户影响力计算中存在交互行为与用户自身因素分析不全面的问题,提出了微博用户影响力计算方法MBUI-SFIM(Micro-blog userinfluence based on user’s self-factors and interaction computing model)。该方法考虑了微博用户直接影响力和间接影响力两个方面:在用户直接影响力计算中,通过对用户的自身因素如微博用户粉丝数、用户活跃度、近期微博质量等的分析,计算出用户的初始影响力,然后分析用户互动行为如用户的微博可见率、微博用户互动系数,计算出用户传播能力,最后将初始影响力与用户传播能力相结合,基于改进PageRank算法计算出用户直接影响力;在用户间接影响力计算中,通过对用户网络图连接结构进行分析,根据不相邻用户连接路径的不同,将用户间接影响具体分为简单路径、重复路径、复杂路径3种情况进行讨论,从而计算出用户间接影响力。实验结果表明,相比PageRank算法和MR-UIRank算法,所提算法在用户排名准确性上分别提高了14.8%和8.3%。

Weibo users with high-impact play an important role in commodity marketing and social publicity guidance,so mining high-impact users becomes a hot research issue in Weibo social networks.As for the problems of incomplete behavior analysis of interaction behavior and user’s own factors in calculation of micro-blog user influence,the micro-blog user influence based on user’s self-factors and interactiont computing model was proposed.This method considers the direct influence and indirect influe-nce of Weibo users.In the user’s direct influence calculation phase,the initial influence of the user is calculated by analyzing the user’s own factors such as the number of fans of Weibo users,user activity,and recent microblog quality.Then the user interaction behavior is analyzed,such as the user’s microblog visibility rate,microblog user interaction coefficient,so as to calculate the user communication ability.Finally,by combining the initial influence with the user communication ability,the user’s direct influe-nce is cakulated based on the improved PageRank algorithm.In the calculation of user indirect influence phase,through the analysis of the connection structure of the user network diagram and according to the different connection paths of non-adjacent users,the indirect impact of the user is divided into three categories:simple path,repeated path and complex path,then the user indirect influence is calculated.The experimental results show that the proposed algorithm is 14.8%and 8.3%higher than the PageRank algorithm and the MR-UIRank algorithm in terms of the user ranking accuracy.