International Journal of Advances in Scientific Research and Engineering (ijasre) E-ISSN : 2454-8006 DOI: 10.31695/IJASRE.2025.3.3 Volume 11, Issue 3 March - 2025 https://ijasre.net/ Page 26 Subject Review: Cyberbullying and Detection Methods Amal Abbas Kadhim 1 , Zainab Khyioon Abdalrdha 2 , and Wedad Abdul Khuder Naser 3 1 Assistant Professor, 2 Assistant Professor, Dr., 3 Assistant Professor 1,3 Mustansiriyah University/ College of Education, Department of Computer Science 2 Mustansiriyah University/ College of Basic Education, Department of Computer Science Baghdad- Iraq _______________________________________________________________________________________ ABSTRACT Cyberbullying is a prevalent issue on social media, causing significant mental and social harm to victims. This review highlights cutting-edge cyberbullying detection technologies, concentrating on machine learning (ML), deep learning (DL), and natural language processing (NLP). The learners are categorized into supervised, unsupervised, and hybrid models, highlighting their pros and cons. This article covers common research datasets, including social media comments, and addresses difficulties including data imbalance, linguistic diversity, and context interpretation. Future efforts include developing context-sensitive models, improving on-the-fly detection, and addressing ethical concerns in automated system deployment. Keywords: Cyberbullying, Deep learning, Bullying detection, Natural Language Processing (NLP). _______________________________________________________________________________________ 1. INTRODUCTION Modern technology relies on the internet for communication, which may encourage undesirable conduct. Such disruptive and harmful behavior includes cyberbullying. Research suggests cyberbullying is to online or digital bullying. It can occur on cellphones, desktops, and other digital platforms as text-based interactions, messages, comments, forum postings, or image sharing. Cyberbullying is the repeated broadcast of cruel or offensive content on social media to injure or distress others [1]. It is a new type of bullying that differs from traditional harassment. Cyberbullying is not limited by time or location, and its anonymity can reach a wider audience and result in more serious abuse. Cyberbullying, especially among younger generations, has increased due to internet connectivity and social media platforms like Facebook, Instagram, and Twitter. This aggressive behavior deeply impacts victims' mental health and lives and can inspire other teens or group members [2]. Text messages, instant chats, social media, and online gaming can all be used for cyberbullying. Statisticbrain.com says Facebook is the most common cyberbullying site [3]. The most common cyberbullying media:  Author-to-recipient email.  Instant messaging online.  Live online chat rooms with like-minded strangers.  Short phone texts.  Social networks unite people with similar backgrounds, interests, and connections.  Personal, corporate, and government sites. Cyberbullying is varied [4][5]:  Flooding: Bullies repeat dumb posts to silence victims.  Masquerade: Bullies imitate victims.  Bullies incite hatred in victims as individuals or groups.  Trolling posts opposing comments to provoke conflict.