The Rise of Social Bots

The Rise of Social Bots from CACM on Vimeo.

The Rise of Social BotsIntroEngineered Social TamperingThe Problem with Malicious Social BotsThe Bot EffectAct Like a Human, Think Like a BotBehavior of Sophisticated BotsTaxonomy of Social BotsGraph-Based Social Bot DetectionCrowdsourcing Bot DetectionFeature-Based Social Bot DetectionCombining Multiple ApproachesMaster of Puppets


Engineered Social Tampering

The Problem with Malicious Social Bots

The Bot Effect

Act Like a Human, Think Like a Bot

The boundary between human-like and bot-like behavior is now fuzzier.

Behavior of Sophisticated Bots

Even more advanced mechanisms can be employed; some social bots are able to “clone” the behavior of legitimate users, by interacting with their friends and posting topically coherent content with similar temporal patterns.

Taxonomy of Social Bots

The field of detecting social bots was relatively new at the time (it still is, and is also ever-evolving) so they propose a simply taxonomy of the classes of bot detection methods…

  1. Systems based on social network information (graph-based)
  2. Systems based on crowdsourcing and leveraging human intelligence
  3. Machine learning methods based on the identification of highly relevant features for discrimination between humans and bots

Sometimes a hard categorization of a detection strategy into one of these three categories is difficult, since some exhibit mixed elements...

Graph-Based Social Bot Detection

The challenge of identifying social bots has been framed in many ways. The Facebook Immune System represents one.

The above image was taken from here not the review paper which these notes focus on.

Crowdsourcing Bot Detection

Feature-Based Social Bot Detection

Feature-based models typically utilize machine learning techniques to encode bot-like and human-like behaviors.

A few benefits of utilizing feature-based methods:

  1. They can be fed to machine learning models and improved
  2. They can be utilized to classify new accounts/social bots at a later date based on the feature model
  3. They can capture different types of bots by capturing orthogonal dimensions of behavior


An example of a feature-based approach is Botometer (formerly Bot or Not?).

As social bots change over time to avoid detection, feature-based methods allow a flexible framework which can be updated and improved upon based on new feature patterns with observed data

Combining Multiple Approaches

Wang et al developed the Renren Sybil detector to implement a system which combines a multitude of the approaches described herein.

This approach has a "Sybil-until proven otherwise" has the benefit of potentially picking up new and as yet unseen bot-like patterns

Other methods which utilize a mixed methods approach are:

Master of Puppets

If social bots are the puppets, additional efforts will have to be directed at finding their “masters.”

Understanding who is behind malicious social bots will be a difficult problem to solve.

Studying platform vulnerabilities has begun as path of research as well

Unfortunately, many basic research questions remain open

A constant limitation of supervised machine learning methods is the need for new and relevant training data since bots can change much faster than scientifically rigorous research can be conducted...


Notes by Matthew R. DeVerna