Forecasting popularity of videos in YouTube

TL;DR

This paper introduces a new prediction process for modeling and forecasting YouTube video popularity, leveraging video classification to identify key factors and improve prediction accuracy over existing models.

Contribution

It presents a novel prediction method that incorporates video classification to better understand and forecast popularity dynamics, reducing prediction errors.

Findings

Prediction process outperforms baseline models in accuracy

Video classification helps identify key factors influencing popularity

Adding popularity criteria improves prediction performance

Abstract

This paper proposes a new prediction process to explain and predict popularity evolution of YouTube videos. We exploit our recent study on the classification of YouTube videos in order to predict the evolution of videos' view-count. This classification allows to identify important factors of the observed popularity dynamics. Our experimental results show that our prediction process is able to reduce the average prediction errors compared to a state-of-the-art baseline model. We also evaluate the impact of adding popularity criteria in our classification.