Computer Science ETDs

Publication Date

Spring 5-11-2024

Abstract

YouTube comments are a unique form of social media, as viewers mainly interact with other viewers through comments sections, and cannot choose to interact with specific people. This lack of control over which comments are presented to them forces users to view spam.

Multiple general patterns of behavior were found in the dataset of YouTube comments. For example, most users posted just after a video’s publication. In addition, users tended to watch videos in the evening over the early morning.

A novel method was found for quantifying the likelihood of coordinated accounts being controlled by one person using time sharing. By finding many correlated accounts which do not overlap in commenting time, it is possible to determine the probability that a clique of accounts are controlled by one person or system.

Lastly, by examining topic vectors, it is possible to see that similar videos tend to have similar comments

Language

English

Keywords

YouTube Comments, Inorganic Behavior, Inorganic Comments, Shotgun Comments, Astroturf Comments

Document Type

Thesis

Degree Name

Computer Science

Level of Degree

Masters

Department Name

Department of Computer Science

First Committee Member (Chair)

Mueen Abdullah

Second Committee Member

Eirini Tsiropoulou

Third Committee Member

Shuang Luan

Download

Share

COinS