Author:
Perumal S. Venkatesh,Joyce Pamila J.C. Miraclin
Abstract
Social media platforms have seen an increase in the prevalence of cyberbullying. Protecting social media platforms against cyberbullying is essential as social media is extensively used among people of all ages. Events of cyberbullying have been rising, especially among young individuals who spend most of their time switching between various social media sites. This study gives an overview of the existing research on the categorization and detection of cyberbullying using several methods from the Deep learning and Machine learning field like Convolutional Neural Network, Recurrent Neural Network, Long Short -Term Memory, Gated Recurrent Unit, Bi-GRU-Attention-CapsNet, Support Vector Machine, Random Forest, Naive Bayes, and k-Nearest Neighbor, along with the study that examines the effects of various feature extraction techniques like Term frequency and Inverse Document Frequency, Information Gain, Dolphin Echolocation Algorithm, and Improved Dolphin Echolocation Algorithm.
Publisher
Inventive Research Organization
Reference14 articles.
1. [1] All the Latest Cyberbullying Statistics for 2023(online). Available: https://www.broadbandsearch.net/blog/cyber-bullying-statistics.
2. [2] Summary of Our Cyberbullying Research (2007-2021) (online). Available: https://www.cyberbullying.org/summary-of-our-cyberbullying-research.
3. [3] R. Zhao, A. Zhou, and K. Mao, ‘‘Automatic detection of cyberbullying on social networks based on bullying features,’’ in Proc. 17th Int. Conf. Distrib. Comput. Netw, Jan. 2016, pp. 1–6.
4. [4] S. Minaee, E. Azimi, and A. Abdolrashidi, “Deep-sentiment: Sentiment analysis using ensemble of cnn and bi-lstm models”, arXiv Prepr. arXiv1904.04206, 2019.
5. [5] V. Banerjee, J. Telavane, P. Gaikwad, and P. Vartak, ‘‘Detection of cyberbullying using deep neural network’’ in Proc. 5th Int. Conf.Adv. Comput. Commun. Syst. (ICACCS), Mar. 2019, pp. 604–607.