Recurrent Neural Networks in Predicting the Popularity of Online Social Networks Content: A Review

Abstract

An online social network is a web platform that individuals use to make social relationships with people who share similar interests, activities, connections, and backgrounds. All online social networks differ in the number of features they provide and their format. In recent years, drastic growth has been seen in the users of online social networks like Flickr, Instagram, Pinterest, Twitter, etc. Among all the features of online social networks, content sharing is the one being widely used by individual users and large organizations. Due to this, content popularity prediction has been extensively studied nowadays, considering various aspects related to it. The study throws light on the use of machine learning techniques in this field. Various algorithms have been used to handle popularity prediction, including classification, regression, and clustering techniques. It is feasible to extract the essential information from such content using machine learning algorithms and utilize the retrieved information in a variety of ways, the majority of which are commercial in nature. The goal of this study is to review and analyze various recurrent neural network (RNN) approaches for predicting the popularity of social media content.