Sequential prediction learning framework and algorithm
This is the implementation of our paper “Sequential Prediction of Social Media Popularity with Deep Temporal Context Networks“.
Dataset
To successfully test performance, we created TPIC Dataset, a temporal popularity image collection dataset.
Overview
Our DTCN contains three main components, from embedding, learning to predicting. With a joint embedding network, we obtain a unified deep representation of multi-modal user-post data in a common embedding space. Then, based on the embedded data sequence over time, temporal context learning attempts to recurrently learn two adaptive temporal contexts for sequential popularity. Finally, a novel temporal attention is designed to predict new popularity (the popularity of a new user-post pair) with temporal coherence across multiple time-scales.
Environment
The code is pure python.