Classification of group behaviors in social media via social behavior grammars

Georgiy Levchuk; Lise Getoor; Marc Smith

doi:10.1117/12.2050823

18 June 2014 Classification of group behaviors in social media via social behavior grammars

Georgiy Levchuk, Lise Getoor, Marc Smith

Proceedings Volume 9097, Cyber Sensing 2014; 909707 (2014) https://doi.org/10.1117/12.2050823
Event: SPIE Defense + Security, 2014, Baltimore, MD, United States

Abstract

The increasing use of online collaboration and information sharing in the last decade has resulted in explosion of criminal and anti-social activities in online communities. Detection of such behaviors are of interest to commercial enterprises who want to guard themselves from cyber criminals, and the military intelligence analysts who desire to detect and counteract cyberwars waged by adversarial states and organizations. The most challenging behaviors to detect are those involving multiple individuals who share actions and roles in the hostile activities and individually appear benign. To detect these behaviors, the theories of group behaviors and interactions must be developed. In this paper we describe our exploration of the data from collaborative social platform to categorize the behaviors of multiple individuals. We applied graph matching algorithms to explore consistent social interactions. Our research led us to a conclusion that complex collaborative behaviors can be modeled and detected using a concept of group behavior grammars, in a manner analogous to natural language processing. These grammars capture constraints on how people take on roles in virtual environments, form groups, and interact over time, providing the building blocks for scalable and accurate multi-entity interaction analysis and social behavior hypothesis testing.

Citation Download Citation

Georgiy Levchuk, Lise Getoor, and Marc Smith "Classification of group behaviors in social media via social behavior grammars", Proc. SPIE 9097, Cyber Sensing 2014, 909707 (18 June 2014); https://doi.org/10.1117/12.2050823

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available