Predicting the popularity of online articles with random forests
Gitte Vanwinckelen, Wannes Meert · Lirias · 2014
In this paper, we describe our submission to the predictive web analytics Discovery Challenge at ECML/PKDD 2014. The main goal of the challenge was to predict the number of visitors of a web page 48 hours in the future after observing this web page for an hour. An additional goal was to pre- dict the number of times the URL appeared in a tweet on Twitter and the number of times a Facebook message con- taining the URL was liked. We present an analysis of the time series data generated by the Chartbeat web analytics engine, which was made available for this competition, and the approach we used to predict page visits. Our model is based on random forest regression and learned on a set of features derived from the given time series data to capture the expected amount of visits, rate of change and temporal effect. Our approach won second place for predicting the number of visitors and the number of Facebook likes, and first place for predicting the number of tweets.