Grid-based recommendation algorithms view users and items as abstract nodes, and the information utilised by the algorithm is hidden in the selection relationships between users and items. Although these relationships can be easily handled, much useful information is overlooked, resulting in a less accurate recommendation algorithm. The aim of this paper is to propose improvements on the standard substance diffusion algorithm, taking into account the influence of the user’s rating on the recommended item, adding a moderating factor, and optimising the initial resource allocation vector and resource transfer matrix in the recommendation algorithm. An average ranking score evaluation index is introduced to quantify user satisfaction with the recommendation results. Experiments are conducted on the MovieLens training dataset, and the experimental results show that the proposed algorithm outperforms classical collaborative filtering systems and network structure based recommendation systems in terms of recommendation accuracy and hit rate.

Online social networks are increasingly connecting people around the world. Influence maximization is a key area of research in online social networks, which identifies influential users during information dissemination. Most of the existing influence maximization methods only consider the transmission of a single channel, but real-world networks mostly include multiple channels of information transmission with competitive relationships. The problem of influence maximization in an environment involves selecting the seed node set for certain competitive information, so that it can avoid the influence of other information, and ultimately affect the largest set of nodes in the network. In this paper, the influence calculation of nodes is achieved according to the local community discovery algorithm, which is based on community dispersion and the characteristics of dynamic community structure. Furthermore, considering two various competitive information dissemination cases as an example, a solution is designed for self-interested information based on the assumption that the seed node set of competitive information is known, and a novel influence maximization algorithm of node avoidance based on user interest is proposed. Experiments conducted based on real-world Twitter dataset demonstrates the efficiency of our proposed algorithm in terms of accuracy and time against notable influence maximization algorithms.