The School of Computer Science is pleased to present…
Online Sexual Predator detection
MSc Thesis Defense by: Muhammad Moeed Khalid
Date: Wednesday, January 18, 2023
Time: 12:00 pm – 1:30 pm
Location: Essex Hall, Room 122
Reminder: Recording of your attendance is mandatory – Part I: QR Code, Part II: Sign-in sheet.
Abstract:
Online sexual abuse is a very concerning yet severely overlooked vice of modern society. With more children being on the Internet and with the ever-increasing advent of web applications such as online chatrooms and multiplayer games, preying on vulnerable users has become more accessible for predators. In recent years, there has been work on detecting online sexual predators using Machine Learning techniques. Such work has trained on severely imbalanced datasets, and imbalance is handled via manual trimming of over-represented labels. In this work, we first tackle the problem of imbalance and then improve the effectiveness of the underlying classifiers. Our evaluation of the proposed sampling approach on PAN benchmark dataset shows performance improvements on several classification metrics compared to prior methods that otherwise require hands-crafted sampling of the data. We also compare our results to Deep Neural Networks to see how much effect the context of the conversation has on our results.
Keywords: Natural Language Processing, Machine Learning, Deep Learning, Data Imbalance, Classification
MSc Thesis Committee:
Internal Reader: Dr. Dima Alhadidi
External Reader: Dr. Jagdish Pathak
Advisors: Dr. Alioune Ngom / Dr. Hossein Fani
Chair: Dr. Kalyani Selvarajah
Bookings
This event is fully booked.
No Responses