Predicting Popularity of Twitter Accounts through the Discovery of Link-Propagating Early Adopters

TL;DR

This paper introduces a method to predict the future popularity of new Twitter accounts by identifying early adopters who tend to find valuable information sources before others, using link propagation analysis.

Contribution

The paper presents a novel approach to rank new Twitter accounts based on inferred link copying behavior of early adopters, requiring only local graph information.

Findings

Method outperforms baseline rankings for new accounts.

Effective in early detection of promising accounts.

Relies solely on local neighbor information in Twitter graph.

Abstract

In this paper, we propose a method of ranking recently created Twitter accounts according to their prospective popularity. Early detection of new promising accounts is useful for trend prediction, viral marketing, user recommendation, and so on. New accounts are, however, difficult to evaluate because they have not established their reputations, and we cannot apply existing link-based or other popularity-based account evaluation methods. Our method first finds "early adopters", i.e., users who often find new good information sources earlier than others. Our method then regards new accounts followed by good early adopters as promising, even if they do not have many followers now. In order to find good early adopters, we estimate the frequency of link propagation from each account, i.e., how many times the follow links from the account have been copied by its followers. If its followers have copied many of its follow links in the past, the account must be an early adopter, who find good information sources earlier than its followers. We develop a method of inferring which links are created by copying which links. One advantage of our method is that our method only uses information that can be easily obtained only by crawling neighbors of the target accounts in the current Twitter graph. We evaluated our method by an experiment on Twitter data. We chose then-new accounts from an old snapshot of Twitter, compute their ranking by our method, and compare it with the number of followers the accounts currently have. The result shows that our method produces better rankings than various baseline methods, especially for new accounts that have only a few followers.