Cyberbullying detection based on the fusion of DistilBERT and SIMHASH Technique

The advent of social network sites increases the bullying content in textual and visual formats. Bullying content disheartened a user or community to a great extent. Also detection of cyberbullying content is a challenging task, especially in online social networks where individuals can be harassed or harmed. .Recently, using pre-trained language models has played a pivotal role in solving this problem reasonably. In this paper, we employed a fusion of a transformer-based model and the SIMHASH technique to solve this classification problem. We consider a readily available cyberbullying dataset. We conducted a comparative study among state-of-the-art models to check the proposed model’s efficacy. The proposed model provides a promising result and outperforms.