Recommendation Algorithm Based on Social Influence Diffusion

Social influence is everywhere in people’s lives. It controls users’ activities in social networks. Understanding the mechanism of interactions between users in social networks can benefit various applications, such as recommendations. Traditional recommendation systems based on collaborative filtering suppose that the behaviors of users are independent of each other and ignore the influence relationships among users. However, different historical behaviors and social relationships of users result in different influences among users. First, the complete user behavior sequences are fed into a recurrent neural network to capture long term patterns of user interest in items. Secondly, a self-attention network is used to obtain short lived interests of users. Then the outputs of the recurrent neural network as queries are fed into another self-attention network to obtain user representations that combine transient effect of and long term patterns of users’ interests, thereby predicting the ratings of users to items. Finally, the proposed recommendation system is used to recommend products that need to be promoted to the maximum number of users. The proposed method is verified to outperform the state-of-the-art algorithms on three real-world datasets.