Recurrent Neural Networks for Online Video Popularity Prediction

TL;DR

This paper introduces a Long-term Recurrent Convolutional Network (LRCN) for predicting online video popularity using only visual cues, achieving significant performance improvements on Facebook video data.

Contribution

The paper presents a novel LRCN-based approach for popularity prediction that leverages sequential visual data, outperforming traditional shallow methods.

Findings

Over 30% improvement in prediction accuracy.

Effective use of visual cues alone for popularity prediction.

Potential to assist content creators in understanding video performance.

Abstract

In this paper, we address the problem of popularity prediction of online videos shared in social media. We prove that this challenging task can be approached using recently proposed deep neural network architectures. We cast the popularity prediction problem as a classification task and we aim to solve it using only visual cues extracted from videos. To that end, we propose a new method based on a Long-term Recurrent Convolutional Network (LRCN) that incorporates the sequentiality of the information in the model. Results obtained on a dataset of over 37'000 videos published on Facebook show that using our method leads to over 30% improvement in prediction performance over the traditional shallow approaches and can provide valuable insights for content creators.