Recurrent Neural Networks for Online Video Popularity Prediction
This work addresses the problem of predicting video popularity for content creators in social media, representing an incremental advancement by applying existing deep learning architectures to this domain.
The paper tackles online video popularity prediction by framing it as a classification task using only visual cues, achieving over 30% improvement in prediction performance compared to traditional shallow approaches on a dataset of over 37,000 Facebook videos.
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.