Understanding and combating link farming in the twitter social network

By Saptarshi Ghosh, Bimal Viswanath, Farshad Kooti, Naveen Kumar Sharma, Gautam Korlam, Fabrício Benevenuto, Niloy Ganguly, Krishna P. Gummadi. The Web Conference, 2012

409 citations recorded by the source corpus.

Subfields: Information Systems, Sociology and Political Science, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/a26438f3d8e6954f95bcf760a83b0751610d4df0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

In Sociology and Political Science

In Statistical and Nonlinear Physics

Citations in the corpus

FRAUDAR: Bounding Graph Fraud in the Face of Camouflage (2016, methodology): “Several methods have used HITS [15]-like ideas to detect fraud in graphs [3,6,9,11,30].”
Faking Sandy: characterizing and identifying fake images on Twitter during Hurricane Sandy (2013, background): “characterized social farming on Twitter, and also proposed a methodology to combat link farming [11].”
SybilFuse: Combining Local Attributes with Global Structure to Perform Robust Sybil Detection (2018, background): “Ghosh et al. [22] showed that on Twitter, a link farming phenomenon is widespread, in which certain benign accounts blindly follow back accounts who follow them.”
Exploiting Temporal Dynamics in Sybil Defenses (2015, background): “Ghosh et al. [10] showed that link farming is widespread on Twitter and that a majority of attack edges are farmed from a small fraction of Twitter users.”
Strength in Numbers: Robust Tamper Detection in Crowd Computations (2015, background): “Link farming [21] is a well-studied problem in Twitter and their defining traits are as follows: they have a large number of followers (more than 1,000), a following per follower ratio in the range [0.”
Sampling Content from Online Social Networks (2015, methodology): “Furthermore, Lists have an additional advantage: List names and other metadata can be used to infer the topical expertise of the members of the Lists, as shown in our prior studies [Ghosh et al. 2012a; Sharma et al. 2012] as well as in other recent studies [Wagner et al. 2012; Wu et al. 2011].”
The Paradigm-Shift of Social Spambots: Evidence, Theories, and Tools for the Arms Race (2017, background): “We also highlight the diﬃculties for OSN administrators to take appropriate countermeasures against the takeover of evolving spambots.”
SybilBlind: Detecting Fake Users in Online Social Networks without Manual Labels (2018, background): “, social capitalists [12]) will accept such friend requests with a relatively high probability, making the Sybils embed to the benign region, most benign users will not accept these friend requests [12].”
REV2: Fraudulent User Prediction in Rating Platforms (2018, background): “Random-walk based algorithms have been developed to detect trolls [36] and link farming from collusion on Twitter [6].”