Copyright © 2025 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{167504,
        author = {Zara Ashreen and Mohammed Waheeduddin Hussain and Sridhar Gummalla},
        title = {ANALYSING AND DETECTING CYBERBULLYING IN SOCIAL PLATFORMS },
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {3},
        pages = {1514-1520},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=167504},
        abstract = {Social networking and communication have been accelerated by information and communication technologies, yet cyberbullying presents serious problems. The cumbersome and ineffective processes currently in place for reporting and prohibiting cyberbullying are relied on the user. For automated cyberbullying identification, traditional machine learning and transfer learning techniques were investigated. An organized annotation procedure and an extensive dataset were employed in the study. The Conventional Machine Learning technique used term lists, psycholinguistics, textual, sentiment and emotive, static and contextual word embeddings, and toxicity characteristics. The use of toxicity features for cyberbullying identification was first demonstrated by this study. The word Convolutional Neural Network (Word CNN) showed similar performance when its contextual embeddings were selected based on their higher F-measure. When supplied separately, toxicity characteristics, embeddings, and textual features raise the bar. In this case, linear SVC was not as effective of handling high-dimensionality characteristics and training time. By using Word CNN for fine-tuning, Transfer Learning was able to achieve a faster training computation than the base models. Furthermore, the implementation of Flask web for cyberbullying detection produced the maximum accuracy. For reasons of privacy, the reference to the particular dataset name was removed.},
        keywords = {},
        month = {August},
        }