Twitter spammer detection using data stream clustering

By Zachary Miller, Brian Dickinson, William Deitrick, Wei-Gang Hu, Alex Hai Wang. Information Sciences, 2014

343 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/5a28d75950960f4d6d9d328f30c7f003ecb28f57

How researchers see this paper

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

In Computer Networks and Communications

In Information Systems

In Statistical and Nonlinear Physics

Citations in the corpus

The Paradigm-Shift of Social Spambots: Evidence, Theories, and Tools for the Arms Race (2017, methodology): “We have implemented the system proposed in [30] to cluster the accounts of our 2 test sets.”
Finding and Characterizing Information Warfare Campaigns (2020, methodology): “Stream-based approaches extract features from a given topical stream or twitter stream sample.”
Contrast Pattern-Based Classification for Bot Detection on Twitter (2019, methodology): “[40] have proposed to use the clustering approach to find groups based on features of either tweet account or account usage.”
Deep Neural Networks for Bot Detection (2018, unknown): “the examples, suggesting that the LSTM hidden units may correspond to different linguistic features. It has been observed by Cresci etal.[14] that using simple textual features, as seen in prior work [42], reveals ineffective against the more sophisticated social bots we study in this work. We plot ”
Fame for sale: Efficient detection of fake Twitter followers (2015, background): “Academia has mostly focused its attention on spammers, those accounts actively putting their efforts in spreading malware, sending spam, and advertising activities of doubtful legality [1, 2, 3, 4].”
Arming the public with artificial intelligence to counter social bots (2019, unknown): “Early attempts combined multiple features via Euclidean distance and then applied clustering or network community algorithms (Ahmed and Abu-laish, 2013; Miller et al., 2014).”