ABSTRACT
Machine learning is a very useful tool to solve issues in multiple domains such as sentiment analysis, fake news detection, facial recognition, and cyberbullying. In this work, we have leveraged its ability to understand the nuances of natural language to detect cyberbullying. We have further utilized it to detect the subject of cyberbullying such as age, gender, ethnicity, and religion. Further, we have built another layer to detect the cases of misogyny in cyberbullying. In one of our experiments, we created a three-layered architecture to detect cyberbullying , then to detect if it is gender based and finally if it is a case of misogyny or not. In each of our experimentation we trained models with support vector machines, RNNLSTM, BERT and distilBERT, and evaluated it using multiple performance measuring parameters like accuracy, bias, mean square error, recall, precision and F1 score to evaluate each model more efficiently in terms of bias and fairness. In addition to fully supervised learning, we also used weakly supervised learning techniques to detect the cyberbullying and its subject during our experimentations. Finally, we compared the performance of models trained using fully supervised learning and weakly supervised learning algorithms. This comparison further demonstrated that using weak supervision we can develop models to handle complex use cases such as cyberbullying. Finally, the thesis document concludes by describing lessons learned, future work recommendations and the concluding remarks.
ABSTRACT
This research work is concerned with the evaluative study of teaching and learning of English grammatical struc...
Background of the Study
Social media has transformed political journalism, offering platforms for real-time news disseminat...
Chapter One: Introduction
INTRODUCTION
A consumer's right is to receive a high-quality product and not one that poses a health risk. Cow flesh...
Background of the Study: Malaria remains a major public health issue in Nigeria, particularly in rural areas...
Chapter One: Introduction
Background of the Study
Cardiovascular diseases (CVDs) are a leading cause of morbidity and mortality worldwide, contributing significant...
Abstract
This study is titled the implications of ownership structure of insurance companies on policy...
Background of the Study
Teenage pregnancy remains a significant public health concern in Nigeria, with high rates recorded across various...
EXCERPT FROM THE STUDY
Advertisement is primary aim to upsurge the sales of the advertised firms. Fundamentally, it is g...