Modeling Image Virality with Pairwise Spatial Transformer Networks

TL;DR

This paper introduces a pairwise neural network approach to predict image virality online, achieving a 12% improvement over previous methods and providing insights into features influencing virality.

Contribution

It presents a novel pairwise reformulation of virality prediction as an attribute prediction task with a new neural network model that outperforms existing methods.

Findings

Achieved 12% higher prediction accuracy than previous state-of-the-art.

External category supervision improves attribute prediction accuracy.

Model offers insights into features promoting virality.

Abstract

The study of virality and information diffusion online is a topic gaining traction rapidly in the computational social sciences. Computer vision and social network analysis research have also focused on understanding the impact of content and information diffusion in making content viral, with prior approaches not performing significantly well as other traditional classification tasks. In this paper, we present a novel pairwise reformulation of the virality prediction problem as an attribute prediction task and develop a novel algorithm to model image virality on online media using a pairwise neural network. Our model provides significant insights into the features that are responsible for promoting virality and surpasses the existing state-of-the-art by a 12% average improvement in prediction. We also investigate the effect of external category supervision on relative attribute prediction and observe an increase in prediction accuracy for the same across several attribute learning datasets.