Publication Date

12-2019

Date of Final Oral Examination (Defense)

10-25-2019

Type of Culminating Activity

Thesis

Degree Title

Master of Science in Computer Science

Department

Computer Science

Supervisory Committee Chair

Gaby Dagher, Ph.D.

Supervisory Committee Member

Bogdan Dit, Ph.D.

Supervisory Committee Member

Min Long, Ph.D.

Abstract

Social media has changed the way people communicate with each other, and consecutively affected people's ability to empathize in both positive and negative ways. One of the most harmful consequences of social media is the rise of cyberbullying, which tends to be more sinister than traditional bullying given that online records typically live on the internet for quite a long time and are hard to control. In this thesis, we present a three-phase algorithm, called BullyNet, for detecting cyberbullies on Twitter social network. We exploit bullying tendencies by proposing a robust method for constructing a cyberbullying signed network. BullyNet analyzes each tweet to determine its relation to cyberbullying, while considering the context in which the tweet exists in order to optimize its bullying score. We also propose a centrality measure to detect cyberbullies from a cybebullying signed network, and we show that it outperforms other existing measures. We evaluate our method on a dataset of 5.6 million tweets we synthesized and labeled. Our experimental results show that the proposed BullyNet algorithm can detect cyberbullies with high accuracy, while being scalable with respect to the number of tweets.

DOI

10.18122/td/1625/boisestate

Download

Share

COinS