Friend Recommendation System in a Social Network based on Link Prediction Framework using Deep Neural Network

Abstract

Over the last decade, social networking sites have become the most frequent way to connect online, which has led to the rise of underlying friend recommendation structure in social networks which suggests friends to users. Most existing friend recommendation frameworks, unfortunately, merely take into account the number of mutual friends, geo-location, mutual interests and other factors when recommending one person as a friend to another. Meanwhile, a number of recent research have demonstrated the value of deep learning and neural networks in the areas of recommendation systems, as well as recent improvements in the field of recommendation employing various deep learning variations. Thus, in this paper, a personalized friend recommendation system based on a hybrid model that combines link prediction (which is a widely used traditional method in most social media platforms and follows the friend-of-friend approach) with a neural network model for added accuracy and efficiency, is discussed.