A Framework for Early Detection of Cyberbullying in Chinese-English Code-Mixed Social Media Text Using Natural Language Processing and Machine Learning

Abstract

This study develops a new expert system framework to address the issue of early detection of cyberbullying incidents in Chinese-English code-mixed language on social media networks. The framework covers the crawling of session-based social media texts with potential cyberbullying messages with a crowdsourcing web application to systematically retrieve and manually annotate a cyberbullying dataset, and most importantly establishes an explainable artificial intelligence model based on natural language processing algorithm for identification of targeted emotional colloquial slang phrases and machine learning method using Shapley value and transfer learning approach for automatic early detection of cyberbullying incidents in Chinese-English codemixed language.