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

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.

Characterizing and Predicting Reviews for Effective Product Marketing and Advancement

“…Assessment of the idea of information is imperative in various applications, yet it is generally difficult to measure it without human intervention. Similar idea has also been successfully associated with limited scope web diaries with interfacing limits [7].…”

Structural Models of Human Social Interactions in Online Smart Communities: the Case of Region-based Journalists on Twitter

“…Our goal in this section is to investigate if popular journalists interact with similarly popular journalists (a sort of assortativity in popularity) on Twitter and if there is a correlation between the popularity of alters and the intimacy level of the corresponding relationship. In the following, we measure popularity in terms of the number of followers of the account, similarly to [34]. To understand the effect of the popularity of the alters in different ego network layers, we carry out a correlation analysis between the popularity of egos and that of their alters.…”

Analyzing Network Effects on a Fanfiction Community

“…The processes of studying the social network metrics an online community(Andreas Kaltenbrunner et al ), estimation of factors to predict popularity of online news (Ksiazek et al (Ksiazek et al, 2016)), evaluation of network metrics on Wikipedia discussion pages (Laniado et al (Laniado et al, 2011)) , interpretation of models to predict the popularity of online contents based on comments (Lee et al (Lee et al, 2010)), obtention of prediction values for contents future popularity (Ahmed et al (Ahmed et al, 2013) ), anticipation of popular twitter accounts (Imamori et al (Imamori and Tajima, 2016)) and prediction of posts popularity through comment mining (Jamali et. al (Jamali and Rangwala, 2009)) has been a references for our study methodology.…”