Home > Events > CLIP Colloquium: Bert Huang (Virginia Tech)

CLIP Colloquium: Bert Huang (Virginia Tech)

Time: 
Wednesday, November 08, 2017 - 11:00 AM to 12:00 PM
Location: 
3258 A.V. Williams Building

Title: Weakly Supervised Learning for Detection of Online Harassment


Abstract
Detrimental online behavior such as harassment and cyberbullying is becoming a serious, large-scale problem damaging people's lives. This phenomenon is creating a need for automated, data-driven detection of such behaviors. In this talk, I’ll present a machine learning method for detecting online harassment that jointly considers social structure and language usage. To address the elusive nature of online behavior, the learning algorithm uses weak supervision. Annotators provide a small seed vocabulary of bullying indicators, and the algorithm uses a large, unlabeled corpus of social-media interactions to train various models of harassment based on who participates and based on what language is used. The algorithm tries to maximize the agreement between these estimates, unifying different perspectives of the problem. I’ll discuss quantitative and qualitative evaluations of our method on social-media datasets that demonstrate its effectiveness in harassment detection. Then I’ll discuss some bigger-picture questions surrounding the use of machine learning for detection of detrimental online behavior.

Bio: Bert Huang is an assistant professor in the Virginia Tech Department of Computer Science. He investigates machine learning with a special focus on models and data with structure stemming from natural networks. Within this focus, his work addresses open questions on theory, algorithms, and applications.