Cyberbullying is a widespread public health issue affecting roughly a third of teenage Internet users and often resulting in serious consequences such as physical violence, depression, and substance abuse. The goal of this project is to develop software tools to forecast imminent cyberbullying threats and vulnerabilities in online social networks. The approach will build on recent advances in natural language processing, machine learning, and social network analysis. With the resulting cross-platform tool, individuals and communities will be better equipped to intervene in cyberbullying episodes in real-time to reduce harm and improve outcomes.

Team Members

Libby Hemphill (Associate Professor, Communication and Information Studies)
Aron Culotta (Assistant Professor, Computer Science)