Predicting the Popularity of Online News using Social Features

Abstract

Consuming news via social media is an integral part of our lives. Various news agencies use social media as a medium to spread their content. Popularity prediction of news before publication is a challenging task because it depends on a very large user base. Popularity of news on social platform can be represented using number of likes, shares. We have used number of likes as a popularity measure. In this paper, we first find out features on social platform which can affect popularity of an article. These features and content metadata are fed to various machine learning models. These models are used to predict whether an article is going to be popular or not. Tree based models achieve best results for prediction. These models also show that hashtags, usermentions and other social features are important factors which affect popularity of news.