Work

A real-time cyberbully checker

Year: 2024

Type: article

Abstract: This paper introduces a cyberbully checker, an AI-driven tool designed for real-time detection and mitigation of cyberbullying. Serenity, a chat application prototype, demonstrates the checker’s capabilities by using Google’s Perspective API to analyse message toxicity instantly. The application offers user-defined toxicity tolerance levels and alerts both senders and receivers before harmful interactions occur. By integrating these features, Serenity showcases how AI can enhance online safety, empowering users and providing guardian oversight without compromising privacy. This work highlights the potential of AI-driven solutions to create safer digital communication environments for adolescents and vulnerable populations. • AI-driven cyberbully checker enables real-time detection and intervention on digital platforms. • A prototype demonstrates cyberbully checker’s effectiveness in detecting and preventing harmful messages. • Uses Google’s Perspective API for instant toxicity analysis. • Offers customisable toxicity tolerance and lexicon for tailored user protection. • Balances safety and privacy with guardian oversight, supporting adolescent autonomy.

Source: Software Impacts

DOI: 10.1016/j.simpa.2024.100710

Authors: Johnny Chan, Shohil Kishore, Xin Yang

Institution: University of Auckland

Language: English

Topic: Hate Speech and Cyberbullying Detection

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Peace, justice, and strong institutions

Open Access status: gold

Estimated APC paid: $480