Social network node influence maximization method combined with degree discount and local node optimization

Abstract

For the problem of maximizing the influence of nodes in traditional social networks, it is impossible to select nodes and spread the scope of large-scale diffusion simultaneously. Based on local node optimization and degree discount, a new node influence maximization algorithm is proposed (degree discount and local improvement method, DLIM). Firstly, the candidate seed set is optimized. The NAV (Node Approximate Influence Value) function is constructed to calculate the Influence Value of local Node. Determine nodes with similar influence value and select the source node; the similarity method is used to filter and delete nodes with similar influence value. Secondly, a node activation algorithm is proposed to filter candidate nodes with the idea of degree discount. DMAP (degree discount and maximum activation probability) is constructed. The function uses the filtered candidate nodes for global diffusion. Finally, the proposed DLIM algorithm is used to select the seed nodes to optimize the nodes, and the independent cascade propagation model is used to conduct comparative analysis experiments on four real data sets of Wiki-Vote, NetHEPT, NetPHY, and GrQc four real datasets, and with the Independent Cascade (IC). A comparative analysis experiment is carried out on the propagation model. The experimental results show that: the proposed DLIM algorithm improves the propagation range by 11.3% compared with the traditional degree discount algorithm. The time efficiency is four orders of magnitude faster than the traditional degree discount algorithm. The proposed DLIM algorithm is reasonable and effective. It can also be applied in network marketing, product recommendation, and other fields.