A Survey on the Spam Issue in Twitter

Social networks are being leveraged by cyber-criminals to cover a wider range of victims. In Twitter, spammers create several bots and behave in different patterns according to their desired aims. Particularly, spammers can spread malicious links leading to malware or phishing sites. Achievable by engaging in social bonds or responding to trending topics (hashtags). Spammers either spam in an individual manner, otherwise in coordinated communities with a clear insight. Decidedly, reinforcing cyber-security in Twitter is an indispensable fact. Several researchers have been studying the different aspects of spamming in Twitter. This paper includes a background over the information handled in Twitter, and a detailed survey over the papers dealing with the spam issue. The discussed papers have been published from 2010 to 2018. In contrast to other surveys, this paper is not limited to the detection of spammers but it also discusses the approaches to the detection of spam communities, compromized accounts, collective attention spam, and the extraction of cybercrime knowledge. Hence, this study can be considered as an essential step for the design of a unified spam detection framework.

[1]  Kyumin Lee,et al.  Uncovering social spammers: social honeypots + machine learning , 2010, SIGIR.

[2]  Zhiyuan Cheng,et al.  Detecting collective attention spam , 2012, WebQuality '12.

[3]  Charles A. Kamhoua,et al.  Probabilistic Inference on Twitter Data to Discover Suspicious Users and Malicious Content , 2016, 2016 IEEE International Conference on Computer and Information Technology (CIT).

[4]  Devika Subramanian,et al.  Hunting Malicious Bots on Twitter: An Unsupervised Approach , 2017, SocInfo.

[5]  P. Santhi Thilagam,et al.  Discovering spammer communities in twitter , 2017, Journal of Intelligent Information Systems.

[6]  Timothy W. Finin,et al.  CyberTwitter: Using Twitter to generate alerts for cybersecurity threats and vulnerabilities , 2016, 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM).

[7]  Kyumin Lee,et al.  Seven Months with the Devils: A Long-Term Study of Content Polluters on Twitter , 2011, ICWSM.

[8]  Kyumin Lee,et al.  Combating Threats to Collective Attention in Social Media: An Evaluation , 2013, ICWSM.

[9]  Kyumin Lee,et al.  Devils, Angels, and Robots: Tempting Destructive Users in Social Media , 2010, ICWSM.

[10]  Kyumin Lee,et al.  The social honeypot project: protecting online communities from spammers , 2010, WWW '10.

[11]  Thanh Tran,et al.  Revealing and Detecting Malicious Retweeter Groups , 2017, 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM).

[12]  Eva Zangerle,et al.  "Sorry, I was hacked": a classification of compromised twitter accounts , 2014, SAC.

[13]  Chao Yang,et al.  A taste of tweets: reverse engineering Twitter spammers , 2014, ACSAC.

[14]  Prabhjot Kaur,et al.  Spam detection on Twitter: A survey , 2016, 2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom).

[15]  William M. Campbell,et al.  Finding Malicious Cyber Discussions in Social Media , 2015 .

[16]  Maurice van Keulen,et al.  Detecting Hacked Twitter Accounts based on Behavioural Change , 2017, WEBIST.

[17]  Gianluca Stringhini,et al.  COMPA: Detecting Compromised Accounts on Social Networks , 2013, NDSS.

[18]  Wanlei Zhou,et al.  Twitter spam detection: Survey of new approaches and comparative study , 2017, Comput. Secur..

[19]  Chao Yang,et al.  Empirical Evaluation and New Design for Fighting Evolving Twitter Spammers , 2011, IEEE Transactions on Information Forensics and Security.

[20]  Guofei Gu,et al.  Analyzing spammers' social networks for fun and profit: a case study of cyber criminal ecosystem on twitter , 2012, WWW.