Social media platforms have quickly become a primary news source for many users because of their convenience and easy access to information. The increasing reliance on social media as a news source has created an environment where online influencers can manipulate narratives and social network structures, often leading to large-scale influence campaigns with real-world consequences. Previous frameworks developed to characterize these online influence operations provide only generic guidelines for analysis rather than a comprehensive and quantitative approach for assessing and addressing these campaigns. The BEND framework offers a more comprehensive approach through identification of social-cyber maneuvers, or online methods of influence and manipulation, to accurately characterize and address the operations that support broader influence campaign objectives.

My research goal is to develop a robust framework for identifying the occurrence of social-cyber maneuvers, operationalizing the framework, and creating an influence operations assessment to inform decision-makers and provide possible counter-maneuvers to deter influence operations. This thesis builds on the BEND framework as a comprehensive tool for analyzing influence campaigns and their associated online operations.

To accomplish this, first, I provide refined definitions for the social-cyber maneuvers to improve the descriptions of each maneuver and its application to influence campaigns. Then I refine the metrics for detecting and understanding these maneuvers by employing an iterative process using statistical analysis of real-world data. Afterward, I develop a method for implementing the social-cyber maneuver framework on online social networks and creating an assessment of influence campaigns. By applying this social-cyber maneuver framework on Twitter data sets related to the COVID-19 Vaccine, the 2022 US Elections, and the Russian Invasion of Ukraine 2022, I illustrate the BEND framework efficacy while providing insight into how the maneuvers are used in combination over time to support overarching influence campaign objectives.

203 pages

Thesis Committee:
Kathleen M. Carley (Chair)
L Richard. Carley
Hirokazu Shirado
David M. Beskow (University States Military Academy)

James D. Herbsleb, Head, Software and Societal Systems Department
Martial Hebert, Dean, School of Computer Science

Return to: SCS Technical Report Collection
School of Computer Science

This page maintained by reports@cs.cmu.edu