Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{197349,
        author = {S.Indhumathi and Rajeswari P and Thabudharshini S and Pavithra P},
        title = {CYBER BULLYING DETECTION IN SOCIAL NETWORKS USING MACHINE LEARNING AND TRANSFER LEARNING},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {7384-7389},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=197349},
        abstract = {Every digital space not stays safe for long. As social media grows, so does bullying through words - threats, insults, repeated attacks - all showing up more often online. These behaviors take a toll on emotional well-being and make platforms feel risky. Checking everything by hand fails because too much gets posted each second. A smarter way involves teaching machines how to spot harm in text. Here, algorithms learn patterns from past examples of abuse. Work happens inside Google Colab, where models train and adjust through trial. To test them live, an interface built with Gradio lets people type and instantly see results. Some systems rely on classic methods like TF-IDF to pull out key features before deciding if something counts as bullying. Others go further, using advanced transformers that have already learned language deeply elsewhere - and then adapt those skills to this task. Each approach gets tested; outcomes show differences in speed, accuracy, and effort needed. Testing reveals transfer learning works better than traditional methods at grasping context and improving accuracy. What stands out is how the new system handles cyberbullying detection with simplicity, room to grow, and ease of use. Automated filtering becomes more reliable, helping create healthier digital spaces. Performance gains come through smarter adaptation, not just added complexity.},
        keywords = {Cyberbullying detection, Toxic comment filtering, Browser extension, Natural language processing, Client-side AI, Social media safety, Content moderation.},
        month = {April},
        }