Year: 2021
Type: article
Abstract: The purpose of this project is to explore the effectiveness of emotional analysis as a means to automatically moderate content or flag content for manual moderation in order to reduce the workload of human moderators in moderating toxic content online. In this context, toxic content is defined as content that features excessive negativity, rudeness, or malice. This often features offensive language or slurs. The work involved in this project included creating a simple website that imitates a social media or forum with a feed of user submitted text posts, implementing an emotional analysis algorithm from a word emotions dataset, designing a system to configure tolerance thresholds on a per-emotion basis, implementing the process of determining violations of incoming text posts using the configuration, and testing the effectiveness of the emotional analysis algorithm at determining toxic posts using a dataset of posts that have been manually reviewed for toxicity by a group of human moderators.
Author: John A. Shelnutt
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3165624312
