Detecting Spammers on Twitter

By Gabriel Magno, Tiago Rodrigues, Virgílio A. F. Almeida. 2010

890 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/b9695799e5e48122636089667fa9004f84cd9085

How researchers see this paper

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

Citations in the corpus

Man vs. Machine: Practical Adversarial Detection of Malicious Crowdsourcing Workers (2014, background): “FFRatio, blacklisted URLs) or bot-like behaviors [4, 11, 42, 47, 50].”
SybilFuse: Combining Local Attributes with Global Structure to Perform Robust Sybil Detection (2018, background): “It is estimated that tens of millions of Sybil accounts exist in popular social networks such as Facebook and Twitter [2], [3].”
A Survey of Techniques for Event Detection in Twitter (2015, background): “Nevertheless, Twitter characteristics and popularity are particularly alluring for spammers and other content polluters (Lee et al. 2011), to spread advertisements, pornography, viruses, and phishing, or just to compromise system reputation (Benevenuto et al. 2010).”
Understanding and combating link farming in the twitter social network (2012, background): “So the primary motivation for spammers to farm links is to accumulate social capital and thereby, increase the chance that their spam tweets, tagged with hashtags related to the popular trending topics of the day [6,32], would show up higher in search results.”
Information credibility on twitter (2011, background): “This has attracted spammers that use Twitter to attract visitors to (typically) web pages offering products or services [ 4 , 11, 36].”
Serf and turf: crowdturfing for fun and profit (2011, background): “OSNs like Facebook [8], Twitter [11, 32], and Renren [34]. The growing threat posed by this malicious activity has spurred work that aims to detect and stop OSN spam using machine learning techniques [3, 33, 31]. This body of research has focused on analyzing and defending againstthe outwardmanifest”
Twitter spammer detection using data stream clustering (2014, methodology): “Researchers in [4] collected an enormous data set comprised of every known active public account on Twitter as of August 2009.”
SybilBlind: Detecting Fake Users in Online Social Networks without Manual Labels (2018, background): “Approaches in this direction [27,23,4,35,19,37,24,10,31,22] leverage various usergenerated contents (e.”
Trafficking Fraudulent Accounts: The Role of the Underground Market in Twitter Spam and Abuse (2013, unknown): “These include analyzing social graph properties of sybil accounts [6, 33, 34], characterizing the arrival rate and distribution of posts [8], analyzing statistical properties of account profiles [3, 26], detecting spam URLs posted by accounts [27], and identifying common spam redirect paths [15].”
Random Walk Based Fake Account Detection in Online Social Networks (2017, background): “In particular, most studies in this direction [5, 19–22, 24, 27] treat Sybil detection as a supervised learning problem; they extract various features from user-generated contents, behaviors, and local graph structure, and then learn machine learning classifiers using a training dataset consisting o”
Uncovering social network sybils in the wild (2011, background): “Other studies have leveraged Bayesian ﬁlters and SVMs to identify spammers on Twitter [2,17,20] and Facebook [14].”
Empirical Evaluation and New Design for Fighting Evolving Twitter Spammers (2011, background): “The first category of work, such as [32,22,35,34], mainly utilizes machine learning techniques to classify legitimate accounts and spam accounts according to their collected training data and their selections of classification features.”
Seven Months with the Devils: A Long-Term Study of Content Polluters on Twitter (2011, background): “Recently, researchers have begun studies of trending topic spam on Twitter (Irani et al. 2010; Benevenuto et al. 2010).”
Correlating financial time series with micro-blogging activity (2012, background): “[2] present features that can be used to detect spammers and how they differ from relevant users.”
Misinformation in Social Media: Definition, Manipulation, and Detection (2019, background): “Early research in this field regards social media users as a special type of documents [3; 26].”
Democrats, republicans and starbucks afficionados: user classification in twitter (2011, background): “Social media in general and Twitter in particular are the subject of considerable ongoing research work: spam detection research [2], tweet sentiment analysis [1], conversation modeling [20] and more.”
COMPA: Detecting Compromised Accounts on Social Networks (2013, background): “Third, we focus on finding compromised accounts and leave the detection of fake accounts to previous work [5, 6, 7] or to the social network providers themselves.”