A Comparative Exploration of Machine Learning and Graph Deep Learning Models for Discriminatory Speech Detection

In an era marked by digital expansion, discriminatory speech remains a widespread concern, exerting significant societal implications. This study presents an overview of discriminatory speech detection techniques and explores the complexities involved in identifying discriminatory speech by utilizing a variety of datasets from various fields. The importance of preprocessing methods and feature engineering is next examined, opening the door for more in-depth study. Furthermore, the paper delves into traditional Machine Learning (ML) algorithms and state-of-the-art Deep Learning (DL) models along with a crucial component of using graph-based structures with Natural Language Processing (NLP) techniques and the use of graphs to extract contextual information. Using both graphs and NLP algorithms enhances the identification process by uncovering contextual connections within textual data.