Towards Automated Moderation: Enabling Toxic Language Detection with Transfer Learning and Attention-Based Models

Date

2022-01-04

Contributor

Advisor

Department

Instructor

Depositor

Speaker

Researcher

Consultant

Interviewer

Narrator

Transcriber

Annotator

Journal Title

Journal ISSN

Volume Title

Publisher

Volume

Number/Issue

Starting Page

Ending Page

Alternative Title

Abstract

Our world is more connected than ever before. Sadly, however, this highly connected world has made it easier to bully, insult, and propagate hate speech on the cyberspace. Even though researchers and companies alike have started investigating this real-world problem, the question remains as to why users are increasingly being exposed to hate and discrimination online. In fact, the noticeable and persistent increase in harmful language on social media platforms indicates that the situation is, actually, only getting worse. Hence, in this work, we show that contemporary ML methods can help tackle this challenge in an accurate and cost-effective manner. Our experiments demonstrate that a universal approach combining transfer learning methods and state-of-the-art Transformer architectures can trigger the efficient development of toxic language detection models. Consequently, with this universal approach, we provide platform providers with a simplistic approach capable of enabling the automated moderation of user-generated content, and as a result, hope to contribute to making the web a safer place.

Description

Keywords

Text Analytics, hate speech detection, machine learning, natural language processing, text analytics, toxic language identification

Citation

Extent

10 pages

Format

Geographic Location

Time Period

Related To

Proceedings of the 55th Hawaii International Conference on System Sciences

Related To (URI)

Table of Contents

Rights

Attribution-NonCommercial-NoDerivatives 4.0 International

Rights Holder

Local Contexts

Collections

Email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.