Towards More Robust Methods of Cyberbullying Detection Público

Ziems, Caleb (Spring 2020)

Permanent URL: https://etd.library.emory.edu/concern/etds/zs25x960d?locale=pt-BR
Published

Abstract

Cyberbullying is a pervasive problem in online communities. To identify cyberbullying cases in large-scale social networks, content moderators depend on machine learning classifiers for automatic cyberbullying detection. However, existing models remain unfit for real-world applications, largely due to a shortage of publicly available training data and a lack of standard criteria for assigning ground truth labels. In this study, we address the need for reliable data using an original annotation framework. Inspired by social sciences research into bullying behavior, we characterize the nuanced problem of cyberbullying using five explicit factors to represent its social and linguistic aspects. We model this behavior using social network and language-based features, which improves classifier performance. Lastly, we develop a method for inferring the target of aggression in the message thread, and we evaluate this approach on hand-labeled data. These results demonstrate the importance of representing and modeling cyberbullying as a social phenomenon.

Table of Contents

Introduction.............................1

Background..............................4

Data.......................................10

Feature Engineering................16

Model Evaluation....................27

Inferring the Target User.........32

Conclusion.............................36

About this Honors Thesis

Rights statement
  • Permission granted by the author to include this thesis or dissertation in this repository. All rights reserved by the author. Please contact the author for information regarding the reproduction and use of this thesis or dissertation.
School
Department
Degree
Submission
Language
  • English
Research Field
Palavra-chave
Committee Chair / Thesis Advisor
Committee Members
Última modificação

Primary PDF

Supplemental Files