Computing and Informatics

Tourist attraction recommendation algorithms have been developed to meet demand related to tourism, spiritual and cultural pursuits. While many studies have been conducted on such algorithms, problems remain regarding tourist interest point recommendation such as ignoring social information, underutilizing context information, and not capturing node relationships which have limited the recommendation performance and representation capability. This paper proposes an algorithm based on graph convolutional neural networks and collaborative filtering (GCNs-CF) for travel interest point recommendation, using an image denoising encoder (IDE) instead of domain aggregation, to better capture the relationships and features between users and adjacent nodes of travel interest point nodes. An adaptive adjustment of the negative sample gradient size is used to solve the problem of slow convergence of graph convolutional neural network. The experimental results show that the proposed method has a higher recommendation effect than other algorithms.