A Bayesian approach for predicting the popularity of tweets

TL;DR

This paper introduces a Bayesian probabilistic model to predict the future popularity of tweets based on early retweet data and network structure, enabling accurate forecasts within minutes of posting.

Contribution

It presents a novel Bayesian approach that accurately predicts tweet popularity using minimal early retweet observations and network information.

Findings

Accurate short-term predictions of retweet counts

Effective predictions with less than 10% of retweet data observed

Potential applications in understanding social media trends

Abstract

We predict the popularity of short messages called tweets created in the micro-blogging site known as Twitter. We measure the popularity of a tweet by the time-series path of its retweets, which is when people forward the tweet to others. We develop a probabilistic model for the evolution of the retweets using a Bayesian approach, and form predictions using only observations on the retweet times and the local network or "graph" structure of the retweeters. We obtain good step ahead forecasts and predictions of the final total number of retweets even when only a small fraction (i.e., less than one tenth) of the retweet path is observed. This translates to good predictions within a few minutes of a tweet being posted, and has potential implications for understanding the spread of broader ideas, memes, or trends in social networks.