Leveraging Text Sentiment Analysis for Cyberbullying Prevention
ID:78
View protection:Participant Only
Updated time:2025-12-21 13:00:39 Views:193
Online
Abstract
In today’s digital era, cyberbullying is a rising phenomenon with major effects on victims’ mental health and well-being. This Master’s thesis report investigates cyberbullying and presents a unique strategy to prevent it through the use of text sentiment analysis algorithms. The suggested Cyberbullying Prevention using Text Sentiment Analysis Algorithm compares the performance of three models: Convolutional Neural Network-Long Short Term Memory (CNN-LSTM), Support Vector Machine (SVM), and Naive Bayes. The models were trained using a dataset of cyberbullying-related social media postings and communications. The results of the experiment show that the SVM model outperformed the other two models with an accuracy of 92% in detecting instances of cyberbullying. The CNN-LSTM model achieved an accuracy of 88%, while the Naive Bayes model achieved an accuracy of 83%. Social media businesses, schools, and other institutions can utilize the suggested method to detect and prevent cyberbullying in online communication. By detecting cyberbullying early on, steps may be taken to protect victims and foster a safer and better online environment. This study emphasizes the efficacy of utilizing text sentiment analysis algorithms to combat cyberbullying and provides useful insights into the performance of various models in identifying cyberbullying.
Keywords
cyberbull,social media,machine learning,deep learning,classification,convolutional neural network,long short term memory,Natural Language Processing,sentiment analysis,twitter
Post comments