What They Do in Shadows: Twitter Underground Follower Market

TL;DR

This paper investigates Twitter underground follower markets, characterizing their structure, operations, and the quality of services, and develops a model to identify suspicious followers with high accuracy.

Contribution

It provides a comprehensive analysis of Twitter underground markets, including their hierarchy, operational schemes, and introduces a supervised model to detect fake followers.

Findings

Freemium markets have an oligopoly structure with few dominant merchants.

Merchant popularity does not correlate with service quality.

Supervised model achieves 89.2% accuracy in identifying suspicious followers.

Abstract

Internet users and businesses are increasingly using online social networks (OSN) to drive audience traffic and increase their popularity. In order to boost social presence, OSN users need to increase the visibility and reach of their online profile, like - Facebook likes, Twitter followers, Instagram comments and Yelp reviews. For example, an increase in Twitter followers not only improves the audience reach of the user but also boosts the perceived social reputation and popularity. This has led to a scope for an underground market that provides followers, likes, comments, etc. via a network of fraudulent and compromised accounts and various collusion techniques. In this paper, we landscape the underground markets that provide Twitter followers by studying their basic building blocks - merchants, customers and phony followers. We charecterize the services provided by merchants to understand their operational structure and market hierarchy. Twitter underground markets can operationalize using a premium monetary scheme or other incentivized freemium schemes. We find out that freemium market has an oligopoly structure with few merchants being the market leaders. We also show that merchant popularity does not have any correlation with the quality of service provided by the merchant to its customers. Our findings also shed light on the characteristics and quality of market customers and the phony followers provided. We draw comparison between legitimate users and phony followers, and find out key identifiers to separate such users. With the help of these differentiating features, we build a supervised learning model to predict suspicious following behaviour with an accuracy of 89.2%.