Leveraging Social Relationship-Based Graph Attention Model for Group Event Recommendation

Abstract

Recently, event-based social networks(EBSN) such as Meetup, Plancast, and Douban have become popular. As users in the networks usually take groups as an unit to participate in events, it is necessary and meaningful to study effective strategies for recommending events to groups. Existing research on group event recommendation either has the problems of data sparse and cold start due to without considering of social relationships in the networks or makes the assumption that the influence weights between any pair of nodes in the user social graph are equal. In this paper, inspired by the graph neural network and attention mechanism, we propose a novel recommendation model named leveraging social relationship-based graph attention model (SRGAM) for group event recommendation. Specifically, we not only construct a user-event interaction graph and an event-user interaction graph, but also build a user-user social graph and an event-event social graph, to alleviate the problems of data sparse and cold start. In addition, by using a graph attention neural network to learn graph data, we can calculate the influence weight of each node in the graph, thereby generating more reasonable user latent vectors and event latent vectors. Furthermore, we use an attention mechanism to fuse multiple user vectors in a group, so as to generate a high-level group latent vector for rating prediction. Extensive experiments on real-world Meetup datasets demonstrate the effectiveness of the proposed model.