Predicting popularity of online videos using Support Vector Regression

Abstract

In this work, we propose a regression method to predict the popularity of an online video based on temporal and visual cues. Our method uses Support Vector Regression with Gaussian Radial Basis Functions. We show that modelling popularity patterns with this approach provides higher and more stable prediction results, mainly thanks to the non-linearity character of the proposed method as well as its resistance against overfitting. We compare our method with the state of the art on datasets containing over 14,000 videos from YouTube and Facebook. Furthermore, we show that results obtained relying only on the early distribution patterns, can be improved by adding social and visual metadata.

References in corpus (3)

• Kernel methods in machine learning
• Robust dynamic classes revealed by measuring the response function of a social system
• Characterizing the Life Cycle of Online News Stories Using Social Media Reactions

Cited by in corpus (7)

• A Survey of Information Cascade Analysis: Models, Predictions, and Recent Advances
• Applying Machine Learning Techniques for Caching in Edge Networks: A Comprehensive Survey
• Music Popularity: Metrics, Characteristics, and Audio-Based Prediction
• Predicting the Popularity of Micro-videos with Multimodal Variational Encoder-Decoder Framework
• Unsupervised Recurrent Federated Learning for Edge Popularity Prediction in Privacy-Preserving Mobile Edge Computing Networks
• Intrinsic Image Popularity Assessment
• How to Cache Important Contents for Multi-modal Service in Dynamic Networks: A DRL-based Caching Scheme