Detecting Automation of Twitter Accounts: Are You a Human, Bot, or Cyborg?

@article{Chu2012DetectingAO,
  title={Detecting Automation of Twitter Accounts: Are You a Human, Bot, or Cyborg?},
  author={Zi Chu and Steven Gianvecchio and Haining Wang and Sushil Jajodia},
  journal={IEEE Transactions on Dependable and Secure Computing},
  year={2012},
  volume={9},
  pages={811-824}
}
Twitter is a new web application playing dual roles of online social networking and microblogging. [] Key Method Based on the measurement results, we propose a classification system that includes the following four parts: 1) an entropy-based component, 2) a spam detection component, 3) an account properties component, and 4) a decision maker. It uses the combination of features extracted from an unknown user to determine the likelihood of being a human, bot, or cyborg. Our experimental evaluation…

Figures and Tables from this paper

Frustrate Twitter from automation: How far a user can be trusted?
TLDR
This paper distinguishes the trustworthy human users and the automated programs (bots) to make the user understand with whom they are interacting with and observes the difference among human and bot in terms of tweeting behavior, tweet content, account properties and its networking flow characteristics.
Hunting Malicious Bots on Twitter: An Unsupervised Approach
TLDR
This protocol effectively identifies malicious bots in a language-independent, as well as topic and keyword independent framework in real-time in an entirely unsupervised manner and is a useful supplement to existing bot detection tools.
On Profiling Bots in Social Media
TLDR
This work finds many bots that are benign, and proposes a new, broader categorization of bots based on their behaviors, which includes broadcast, consumption, and spam bots.
Human-Bot Interactions : Detection , Estimation , and Characterization
TLDR
This work presents a framework to detect social bots on Twitter, and describes several subclasses of accounts, including spammers, self promoters, and accounts that post content from connected applications.
Discovery and classification of Twitter bots
TLDR
Analysis of a dense crawl of a subset of Twitter traffic, amounting to nearly all interactions by Greek-speaking Twitter users for a period of 36 months, finds botnets that appear for brief intervals and disappear, as well as botnet interaction with user communities and Twitter trending topics.
Detecting Social Bots on Twitter: A Literature Review
TLDR
A review of the recent techniques that have emerged that are designed to differentiate between social bot account and human accounts and examines common aspects such as the classifier, datasets, and selected features employed.
Improved Tweet Bot Detection Using Geo-Location and Device Information
TLDR
By utilizing geo-tagged tweets that provide high-precision location information of users, a new tweet bot detection algorithm is proposed that shows superior bot detection and false alarm probabilities over the conventional result which only uses temporal information.
Twitter bot detection and their influence in hashtag manipulation
TLDR
To assess the influence of users in hashtag manipulation, this research analyzed various categories of Users in a hashtag and made promising conclusions.
Using sentiment to detect bots on Twitter: Are humans more opinionated than bots?
TLDR
By analyzing a large dataset relating to the 2014 Indian election, it is shown that a number of sentimentrelated factors are key to the identification of bots, significantly increasing the Area under the ROC Curve (AUROC).
Bots and Gender Classification on Twitter
TLDR
The goal of this paper is to detect if the author of a Tweet is a bot or a human, and if human, identify the gender of that particular author at PAN-19 evaluation lab.
...
...

References

SHOWING 1-10 OF 60 REFERENCES
What is Twitter, a social network or a news media?
TLDR
This work is the first quantitative study on the entire Twittersphere and information diffusion on it and finds a non-power-law follower distribution, a short effective diameter, and low reciprocity, which all mark a deviation from known characteristics of human social networks.
Who says what to whom on twitter
TLDR
A striking concentration of attention is found on Twitter, in that roughly 50% of URLs consumed are generated by just 20K elite users, where the media produces the most information, but celebrities are the most followed.
@spam: the underground on 140 characters or less
TLDR
A characterization of spam on Twitter finds that 8% of 25 million URLs posted to the site point to phishing, malware, and scams listed on popular blacklists, and examines whether the use of URL blacklists would help to significantly stem the spread of Twitter spam.
Why we twitter: understanding microblogging usage and communities
TLDR
It is found that people use microblogging to talk about their daily activities and to seek or share information and the user intentions associated at a community level are analyzed to show how users with similar intentions connect with each other.
Analysis of Twitter Lists as a Potential Source for Discovering Latent Characteristics of Users
TLDR
It is shown that by using the tweets of all the users in a Twitter list, it is possible to discover characteristics and interests of the Users in that list, even if the users as individuals do not tweet about those interests.
Measurement and Classification of Humans and Bots in Internet Chat
TLDR
This paper conducts a series of measurements on a large commercial chat network and proposes a classification system to accurately distinguish chat bots from human users, which shows that human behavior is more complex than bot behavior.
Your botnet is my botnet: analysis of a botnet takeover
TLDR
This paper reports on efforts to take control of the Torpig botnet and study its operations for a period of ten days, which provides a new understanding of the type and amount of personal information that is stolen by botnets.
Detecting Spam in a Twitter Network
TLDR
This article examines spam around a one-time Twitter meme—“robotpickuplines” and shows the existence of structural network differences between spam accounts and legitimate users, highlighting challenges in disambiguating spammers from legitimate users.
Measurement and analysis of online social networks
TLDR
This paper examines data gathered from four popular online social networks: Flickr, YouTube, LiveJournal, and Orkut, and reports that the indegree of user nodes tends to match the outdegree; the networks contain a densely connected core of high-degree nodes; and that this core links small groups of strongly clustered, low-degree node at the fringes of the network.
HoneyIM: Fast Detection and Suppression of Instant Messaging Malware in Enterprise-Like Networks
TLDR
This paper proposes a novel IM malware detection and suppression mechanism, HoneyIM, which guarantees almost zero false positive on detecting and blocking IM malware in an enterprise-like network.
...
...