论文部分内容阅读
深入挖掘社交网络中传播力较强的个体,并利用其进行产品营销往往会达到事半功倍的效果,影响最大化问题就是在特定社交网络中寻找影响力较大的个体.为了更加准确的评估影响力,本文不仅从节点相似度方面进行改进,而且从信息内容本身出发,基于信息在社交网络中的传播,结合信息词频等信息自身特点来刻画节点的影响力,提出了基于信息词频和节点相似度的影响最大化算法(IMFS,Influence Maximization algorithm based on term Frequency and node Similarity).随后,在真实的社交网络中对该算法进行了实验,并与传统的影响最大化算法对比,实验结果表明由IMFS得到的集合的影响范围大于其他启发式算法的结果,同时算法的运行速度也有相应的提高,说明了本文提出的算法是解决影响最大化问题的有效算法.
In-depth mining of social networks, strong individuals and use their product marketing tend to achieve a multiplier effect, maximize the impact of the problem is to find a particular social network influential individuals.In order to more accurately assess the impact of , This paper not only improves the similarity of nodes, but also based on the information content itself, based on the information dissemination in social networks, combined with the characteristics of information such as information frequency to characterize the influence of nodes, (IMFS, Influence Maximization algorithm based on term Frequency and node Similarity) .Then, the algorithm was tested in real social networks and compared with the traditional maximization algorithm, the experimental results show that the IMFS The range of influence of the set is larger than the results of other heuristics, and the speed of the algorithm is also improved accordingly. It shows that the algorithm proposed in this paper is an effective algorithm to solve the problem of maximizing the impact.