Toward Order-of-Magnitude Cascade Prediction

TL;DR

This paper introduces structural diversity measures to predict whether social media cascades will become viral, achieving high accuracy despite data imbalance and outperforming existing methods.

Contribution

It proposes novel structural diversity features for cascade prediction and demonstrates their effectiveness in classifying viral growth in social networks.

Findings

Achieved 0.69 precision and 0.52 recall in predicting viral cascades.

Structural diversity features outperform baseline and state-of-the-art methods.

Effectively handles severe class imbalance in cascade prediction.

Abstract

When a piece of information (microblog, photograph, video, link, etc.) starts to spread in a social network, an important question arises: will it spread to "viral" proportions -- where "viral" is defined as an order-of-magnitude increase. However, several previous studies have established that cascade size and frequency are related through a power-law - which leads to a severe imbalance in this classification problem. In this paper, we devise a suite of measurements based on "structural diversity" -- the variety of social contexts (communities) in which individuals partaking in a given cascade engage. We demonstrate these measures are able to distinguish viral from non-viral cascades, despite the severe imbalance of the data for this problem. Further, we leverage these measurements as features in a classification approach, successfully predicting microblogs that grow from 50 to 500 reposts with precision of 0.69 and recall of 0.52 for the viral class - despite this class comprising under 2\% of samples. This significantly outperforms our baseline approach as well as the current state-of-the-art. Our work also demonstrates how we can tradeoff between precision and recall.