IRMA-International.org: Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

Machine Learning Models for Automated Hate Speech Detection in Synthetic Content

Machine Learning Models for Automated Hate Speech Detection in Synthetic Content
View Sample PDF
Author(s): Tarni Khatri (Manipal University Jaipur, India), Vibhakar Pathak (Arya College of Engineering and Information Technology, India), Rohit Mittal (Manipal University Jaipur, India)and Manish Mittal (Brainware University, Kolkata, India)
Copyright: 2026
Pages: 12
Source title: Detecting Hate Speech in Human and AI-Generated Content: Techniques, Bias Mitigation, and Ethical Considerations
Source Author(s)/Editor(s): Mohammad Arsalan (Qatar University, Qatar), Mehul Mahrishi (Swami Keshvanand Institute of Technology, India), Ruchi Doshi (Universidad Azteca, Chalco, Mexico), Archika Jain (Swami Keshvanand Institute of Technology, India)and Chandrashekhar Goswami (Sir Padampat Singhania University, India)
DOI: 10.4018/979-8-3373-3063-1.ch014

Purchase

View Machine Learning Models for Automated Hate Speech Detection in Synthetic Content on the publisher's website for pricing and purchasing information.

Abstract

This chapter focuses on how Machine Learning (ML) can help identify and reduce hate speech on the internet. With the growing use of Artificial Intelligence (AI), there is a risk that these systems can unintentionally spread or support hate speech. This often happens because the data used to train these models may contain biased or harmful language, and the models may not fully understand the context in which words are used. The chapter explains how different ML techniques—such as supervised learning (where the model learns from labelled examples), unsupervised learning (where the model finds patterns in data without labels) can be used to detect hate speech in text. The chapter also discusses how we can measure the performance of hate speech detection models using metrics such as precision (how many detected hate speech examples were actually hate speech), recall (how many real hate speech examples were correctly found), F1-score (a balance between precision and recall), and ROC-AUC.

Related Content

Sahar Yousif Mohammed, Maad M. Mijwil, Duaa Hikmat Abbas, Kamal Kant Hiran, Ali Guma, Indu Bala, Aseed Yaseen Rashid Al-Jubori. © 2026. 16 pages.
Kashvi Chaturvedi, Yadnyesh Khapekar, Sunil Sankathala, Aditya Shrivastav, Atharva Haresh Saraf, Susanta Das. © 2026. 24 pages.
Snehal Rahul Rathi, Aditi Meshram, Ritik Narote, Shilpa Prashant Kalantri. © 2026. 24 pages.
Rituraj Jain, Ashish Sharna, Venkateswararao Pulipati, Nausheen Khilji, Rakesh Saxena. © 2026. 30 pages.
Fredrick Kayusi, Linety Juma, Michael Keari Omwenga, Petros Keari Chavula, Maad M. Mijwil, Kamal Kant Hiran, Bismarck Agura Kayus, Manish Tiwari. © 2026. 32 pages.
Neha Yadav, Mayank Singh, Vipin Tyagi. © 2026. 24 pages.
Manish Mittal, Manish Tiwari, Ruchi Doshi, Kamal Kant Hiran. © 2026. 24 pages.
Body Bottom