Goodness-of-fit techniques
Proceedings of the first workshop on Online social networks
Why We Twitter: An Analysis of a Microblogging Community
Advances in Web Mining and Web Usage Analysis
@spam: the underground on 140 characters or less
Proceedings of the 17th ACM conference on Computer and communications security
Phi.sh/$oCiaL: the phishing landscape through short URLs
Proceedings of the 8th Annual Collaboration, Electronic messaging, Anti-Abuse and Spam Conference
Identifying automatic posting systems in microblogs
EPIA'11 Proceedings of the 15th Portugese conference on Progress in artificial intelligence
Canal: scaling social network-based Sybil tolerance schemes
Proceedings of the 7th ACM european conference on Computer Systems
Effects of a soft cut-off on node-degree in the Twitter social network
Computer Communications
Understanding and combating link farming in the twitter social network
Proceedings of the 21st international conference on World Wide Web
Key challenges in defending against malicious socialbots
LEET'12 Proceedings of the 5th USENIX conference on Large-Scale Exploits and Emergent Threats
Understanding the time-series behavioral characteristics of evolutionally advanced email spammers
Proceedings of the 5th ACM workshop on Security and artificial intelligence
For some eyes only: protecting online information sharing
Proceedings of the third ACM conference on Data and application security and privacy
Design and analysis of a social botnet
Computer Networks: The International Journal of Computer and Telecommunications Networking
A bigData platform for analytics on access control policies and logs
Proceedings of the 18th ACM symposium on Access control models and technologies
Detecting stealthy, distributed SSH brute-forcing
Proceedings of the 2013 ACM SIGSAC conference on Computer & communications security
Using naive bayes to detect spammy names in social networks
Proceedings of the 2013 ACM workshop on Artificial intelligence and security
Hi-index | 0.00 |
We present a method for determining whether a Twitter account exhibits automated behavior in publishing status updates known as tweets. The approach uses only the publicly available timestamp information associated with each tweet. After evaluating its effectiveness, we use it to analyze the Twitter landscape, finding that 16% of active accounts exhibit a high degree of automation. We also find that 11% of accounts that appear to publish exclusively through the browser are in fact automated accounts that spoof the source of the updates.