Date of Award
6-2-2021
Document Type
Dissertation
Degree Name
Doctor of Philosophy (PhD)
Department
Computer Science
First Advisor
Nitin Agarwal
Abstract
Online social networks (OSNs) are a major component of societal digitalization. OSNs alter how people communicate, make decisions, form or change their beliefs, attitudes, and behaviors. Thus, they can now impact financial systems and political communication at scale. As one type of OSN, social media platforms such as Twitter, Facebook, YouTube, etc. serve as outlets for users to convey information to an audience as broad or targeted as the user desires. Over the years, these social media platforms have been infected with automated accounts, or bots, that are capable of hijacking conversations, influencing other users and manipulating content dissemination. Although benign bots exist to facilitate legitimate activities, the emphasis is on bots that are created to do harm through social media platforms. Bots that mimic social behaviors of humans are referred to as social bots. Social bots help automate many socio-technical behaviors such as tweeting/retweeting a message, ‘liking’ tweets, following users, and coordinating with or even competing against other bots. Social bots exist as benign bots such as advertising bots, entertainment bots, etc. as well as malicious bots such as spam bots, hackers and influence bots. Some of these bots operate independently and autonomously for years without getting noticed or suspended. Furthermore, some of the more advanced social bots exhibit highly sophisticated coordination and communication patterns with complex organizational structures. Therefore, it is important to understand how users coordinate in general rather than limiting to just social bots. This thesis presents a methodology to assess coordination during online campaigns. It leverages social network theories to understand the structure of a communication network and analyzes various network measures to label communities in a graph. It also leverages existing supervised machine learning models to train and test various levels of coordination.
Recommended Citation
Khaund, Tuja, "Leveraging Social Network Analysis and Supervised Machine Learning to Study Coordination in Online Information Campaigns" (2021). Theses and Dissertations. 1009.
https://research.ualr.edu/etd/1009
