Abstract

Social media platforms enable people to easily communicate with one another, share ideas and express their opinions. Unfortunately, the anonymity provided by platforms such as Twitter and Facebook is more than enough to foster the spread of harmful content. Government agencies, as well as technology companies, are actively working towards finding better means of curbing offensive and objectionable content in social media and contributing to a more welcoming online environment. In this study, I first present a critical literature review on offensive language identification, exploring offensive language datasets and computational models using both machine learning and deep learning. Next, I present a systematic review of OLID annotations with the goal of addressing the known issue of subjectivity and conduct an evaluation using deep learning. This review was a collaboration with two other graduate students as part of our MS Capstone project. Lastly, to benchmark multitask learning (MTL), I apply it on the HASOC Subtrack at FIRE 2021 as it provides a single dataset for multiple subtasks which have been annotated per instance and compare its performance against single task learning (STL).

Publication Date

2026

Document Type

Thesis

Student Type

Graduate

Degree Name

Data Science (MS)

Department, Program, or Center

Computer Science, Department of

College

Golisano College of Computing and Information Sciences

Advisor

Marcos Zampieri,

Advisor/Committee Member

Travis Desell

Campus

RIT – Main Campus

Download

Share

COinS