Journal of Computers, Mechanical and Management

M. Barhate, P. N. Mahalle, V. Patil, R. Yargop, S. Yanpallewar, T. Zade, V. Kothari, A comparative analysis of machine learning techniques for cyberbullying detection, Journal of Information and Communications Technology: Algorithms, Systems and Applications, 2025, 1(1), 25307, https://doi.org/10.64189/ict.25307.

Rights and permissions

© The Author(s) 2025.

Open Access

This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License, which permits the non-commercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as appropriate credit to the original author(s) and the source is given by providing a link to the Creative Commons License and changes need to be indicated if there are any. The images or other third-party material in this article are included in the article's Creative Commons License, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons License and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this License, visit: httpshttps://creativecommons.org/licenses/by-nc/4.0/

Abstract

A major worry in the current digital era is cyberbullying, which primarily affects young people who use Web 2.0-powered social media platforms. It usually entails threatening, degrading, or emotionally harming people via online tools and platforms, which frequently results in major psychological consequences like anxiety, sadness, and low self-esteem. This study uses both publicly available Twitter data and data that has been scraped from the platform to examine how machine learning algorithms can be used to detect and categorize instances of cyberbullying. After the text data is cleaned and processed using vectorization techniques, it is analyzed using a variety of supervised learning algorithms. These include Naive Bayes, Random Forest, Support Vector Machines, Logistic Regression, and ensemble models like AdaBoost and Bagging. Each model is assessed using metrics like accuracy, precision, recall, F1-score, and performance efficiency. The study highlights the importance of fine-tuning for practical application by comparing model results. Along with figuring out how to best identify cyberbullying, the goal is to promote the creation of increasingly sophisticated technologies that can help create a safer online environment. This work helps ongoing efforts to use natural language processing and machine learning to alleviate the negative effects of cyberbullying.

Graphical Abstract

Novelty statement

This study reviews machine learning techniques for cyberbullying with comparative analysis.