Who Will Share My Image? Predicting the Content Diffusion Path in Online Social Networks

TL;DR

This paper introduces Diffusion-LSTM, a deep learning model that predicts the entire diffusion path of images in social networks by combining user and image features with memory, outperforming baselines.

Contribution

The work presents a novel memory-based deep recurrent network that accurately predicts diffusion paths and generalizes to unseen users in social media content sharing.

Findings

Diffusion-LSTM outperforms baseline models in diffusion path prediction.

The model can generate realistic diffusion trees that resemble ground-truth trees.

Mapping users to prototypes enables generalization to new users.

Abstract

Content popularity prediction has been extensively studied due to its importance and interest for both users and hosts of social media sites like Facebook, Instagram, Twitter, and Pinterest. However, existing work mainly focuses on modeling popularity using a single metric such as the total number of likes or shares. In this work, we propose Diffusion-LSTM, a memory-based deep recurrent network that learns to recursively predict the entire diffusion path of an image through a social network. By combining user social features and image features, and encoding the diffusion path taken thus far with an explicit memory cell, our model predicts the diffusion path of an image more accurately compared to alternate baselines that either encode only image or social features, or lack memory. By mapping individual users to user prototypes, our model can generalize to new users not seen during training. Finally, we demonstrate our model's capability of generating diffusion trees, and show that the generated trees closely resemble ground-truth trees.