A Comparison of Different Models for the Detection of Hate Speech

With the increasing usage of social media, we have seen an increase in inflammatory and hate speech along racial and ethnic lines on platforms such as Twitter, Instagram, and Facebook. This issue has become a serious setback for humanity, and in order to address it, we used machine learning to recog...

Full description

Saved in:

Bibliographic Details
Published in:	2022 1st International Conference on Computational Science and Technology (ICCST) pp. 492 - 496
Main Authors:	Lohitha, Bhusarapu, V, Mogana, Amarnath, J Jegan
Format:	Conference Proceeding
Language:	English
Published:	IEEE 09-11-2022
Subjects:	Hate speech Machine learning Machine learning algorithms Social networking (online) Support vector machines Text categorization Training
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	With the increasing usage of social media, we have seen an increase in inflammatory and hate speech along racial and ethnic lines on platforms such as Twitter, Instagram, and Facebook. This issue has become a serious setback for humanity, and in order to address it, we used machine learning to recognise hate speech messages across a variety of datasets. Despite the fact that machine learning has been successful at detecting offensive and hate speech in a variety of English contexts, there is yet no proper study to compare multiple machine learning algorithms that outperform a typical publicly available dataset, to the best of what we have known. With this in mind, we've developed a set of feature engineering approaches and machine learning algorithms to assess the performance of models on a large scale.
DOI:	10.1109/ICCST55948.2022.10040400