Detecting cyberbullying in social media text using natural language processing

Mohd Yasin, Muhammad Firdaus Aiman (2023) Detecting cyberbullying in social media text using natural language processing. Project Report. Melaka, Malaysia, Universiti Teknikal Malaysia Melaka. (Submitted)

	Text (24 Pages) Detecting cyberbullying in social media text using natural language processing.pdf - Submitted Version Download (524kB)
	Text (Full Text) Detecting cyberbullying in social media text using natural language processing.pdf - Submitted Version Restricted to Registered users only Download (1MB)

Abstract

The goal of this project is to find the method that can solve on detecting cyberbullying on social media using natural language processing. Because the selected language is Malay hence there are a lot challenges to overcome. To get the classify the cyberbullying text and determine the best model, we will use Support Vector Machine, Naïve Bayes, Long Short Term Memory, Convolution Neural Network and Bidirectional Encoder Representation from Transformer. This project will make use of 1383 tweet data. The data is separated into two part: training, and testing. The model’s results will evaluate using the confusion matrix such as accuracy, precision, recall and f1 score. In addition the model with highest accuracy can be selected to use for detecting the cyberbullying tweet. Last but not least the model deployment phase will be deploy on more interactive interface or graphical representation using Streamlit in order to test the best model produce in detecting cyberbullying tweet.

Actions (login required)

View Item