Bot Conversations are Different: Leveraging Network Metrics for Bot Detection in Twitter

@article{Beskow2018BotCA,
  title={Bot Conversations are Different: Leveraging Network Metrics for Bot Detection in Twitter},
  author={David M. Beskow and Kathleen M. Carley},
  journal={2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)},
  year={2018},
  pages={825-832}
}
  • David M. Beskow, Kathleen M. Carley
  • Published 1 August 2018
  • Computer Science
  • 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)
Automated social media bots have existed almost as long as the social media platforms they inhabit. Although efforts have long existed to detect and characterize these autonomous agents, these efforts have redoubled in the recent months following sophisticated deployment of bots by state and non-state actors. This research will study the differences between human and bot social communication networks by conducting an account snow ball data collection, and then evaluate features derived from… 

Figures and Tables from this paper

You Are Known by Your Friends: Leveraging Network Metrics for Bot Detection in Twitter
TLDR
This research will study the differences between human and bot social communication networks by conducting an account snow ball data collection, and then evaluate network, content, temporal, and user features derived from this communication network in several bot detection machine learning models.
Its all in a name: detecting and labeling bots by their name
TLDR
This research proposes a multi-model ‘tool-box’ approach in order to conduct detection at various tiers of data granularity and uses random string detection applied to user names to filter twitter streams for bot accounts.
Leveraging node neighborhoods and egograph topology for better bot detection in social graphs
TLDR
This paper proposes an approach to fake account and bot classification which leverages the social graph’s topology and differences in egographs of legitimate and fake user accounts to improve identification of the latter.
#BDST: BOT DETECTION SUPPORT TOOL FOR HUMAN ANNOTATORS OF TWITTER DATA
The human annotation of social bots is an essential task for the training of new algorithms and bot detection techniques. However, identifying bot users on social media is tricky and error-prone,
Bot Detection on Social Networks Using Persistent Homology
TLDR
The experimental results suggest that using the higher-order topological features coming from persistent homology is promising in bot detection and more effective than using classical graph-theoretic structural features.
Twitter bot detection using supervised machine learning
In the world of Internet and social media, there are about 3.8 billion active social media users and 4.5 billion people accessing the internet daily. Every year there is a 9% growth in the number of
Analyzing time series activity of Twitter political spambots
TLDR
This work collected a large sample of tweets during the post-electoral conflict in the US in 2020 and performed supervised and non-supervised statistical learning techniques to quantify the predictive power of time-series features for human-bot recognition.
Bot-Match: Social Bot Detection with Recursive Nearest Neighbors Search
TLDR
The Bot-Match methodology is presented, in which social media embeddings that enable a semi-supervised recursive nearest neighbors search to map an emerging social cybersecurity threat given one or more seed accounts are evaluated.
Malicious Bot Detection in Online Social Networks: Arming Handcrafted Features with Deep Learning
TLDR
This paper proposes a novel framework that incorporates handcrafted features and automatically learned features by deep learning methods from various perspectives and automatically makes the balance between them to make the final prediction toward detecting malicious bots.
Identifying Twitter Bots Using a Convolutional Neural Network
TLDR
Convolutional neural networks are seen as a promising machine learning technique for Twitter bot detection when evaluating the best performing approach on the actual test data set of the CLEF 2019 Bots Profiling Subtask.
...
...

References

SHOWING 1-10 OF 38 REFERENCES
BotOrNot: A System to Evaluate Social Bots
TLDR
BotOrNot, a publicly-available service that leverages more than one thousand features to evaluate the extent to which a Twitter account exhibits similarity to the known characteristics of social bots, is presented.
Using Random String Classification to Filter and Annotate Automated Accounts
TLDR
This research proposes using random string detection applied to user names to filter twitter streams for potential bot accounts and thereby generating annotated data.
Online 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.
Bot-hunter: A Tiered Approach to Detecting & Characterizing Automated Activity on Twitter
TLDR
This work seeks to lay the groundwork for bot-hunter, a Tiered Approach to bot detection and characterization, while simultaneously presenting an event based method for annotating data.
Deep Neural Networks for Bot Detection
Social Bots: Human-Like by Means of Human Control?
TLDR
It is concluded that hybridization is a challenge for current detection mechanisms and has to be handled with more sophisticated approaches to identify political propaganda distributed with social bots.
DeBot: Twitter Bot Detection via Warped Correlation
TLDR
It is observed that some bots can avoid Twitter's suspension mechanism and remain active for months, and, more alarmingly, it is shown that DeBot detects bots at a rate higher than the rate Twitter is suspending them.
People Are Strange When You're a Stranger: Impact and Influence of Bots on Social Networks
TLDR
Results show that a basic social probing activity can be used to acquire social relevance on the network and that the so-acquired popularity can be effectively leveraged to drive users in their social connectivity choices.
Bots , # StrongerIn , and # Brexit : Computational Propaganda during the UK-EU Referendum
TLDR
It is found that political bots have a small but strategic role in the referendum conversations: the family of hashtags associated with the argument for leaving the EU dominates, different perspectives on the issue utilize different levels of automation.
Social Bots Distort the 2016 US Presidential Election Online Discussion
TLDR
The findings suggest that the presence of social media bots can indeed negatively affect democratic political discussion rather than improving it, which in turn can potentially alter public opinion and endanger the integrity of the Presidential election.
...
...