Algebraic reputation model RepRank and its application to spambot detection

TL;DR

This paper introduces RepRank, a Markov chain-based reputation model for social network analysis, specifically targeting spam and bot detection, demonstrating its effectiveness through comparison with TrustRank on a large Russian Twitter dataset.

Contribution

The paper presents RepRank, a novel reputation propagation model that incorporates trust and anti-trust, with an effective numerical computation method and empirical comparison to existing models.

Findings

RepRank effectively detects spam and bots in social networks.

RepRank outperforms TrustRank in accuracy on the tested dataset.

The model is scalable to large social network datasets.

Abstract

Due to popularity surge social networks became lucrative targets for spammers and guerilla marketers, who are trying to game ranking systems and broadcast their messages at little to none cost. Ranking systems, for example Twitter's Trends, can be gamed by scripted users also called bots, who are automatically or semi-automatically twitting essentially the same message. Judging by the prices and abundance of supply from PR firms this is an easy to implement and widely used tactic, at least in Russian blogosphere. Aggregative analysis of social networks should at best mark those messages as spam or at least correctly downplay their importance as they represent opinions only of a few, if dedicated, users. Hence bot detection plays a crucial role in social network mining and analysis. In this paper we propose technique called RepRank which could be viewed as Markov chain based model for reputation propagation on graphs utilizing simultaneous trust and anti-trust propagation and provide effective numerical approach for its computation. Comparison with another models such as TrustRank and some of its modifications on sample of 320000 Russian speaking Twitter users is presented. The dataset is presented as well.