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.
BACKGROUND OF THE STUDY
Job satisfaction is an attitude that arises from the balance and summation of n...
ABSTRACT
Poor urban planning in the face of rapid urbanization and unplanned settlements is regarded as one of the major problems many ur...
ABSTRACT
Countries undergoing democratic transitions experience a wide range of long-term outcomes. Dep...
ABSTRACT: This study examined the impact of early childhood education on...
ABSTRACT
Occupation hazards constitute a major threat to an active workforce. Fricidences such as back...
ABSTRACT
This research work investigated the Influence of Monitoring and Evaluation Strategies on Teaching and Learning in Secondary Scho...
Background of the Study
The Nigeria marketing environment today is one of aggressive and unfriendly competition among both manufacturers...
ABSTRACT: This research investigates the benefits of early childhood education in fostering respect for diversity among young children. Object...
ABSTRACT: THE IMPACT OF CLIMATE CHANGE ON THE BUSINESS ENVIRONMENT
This study aims to:...
ABSTRACT
This study was carried out on the evaluation of youths participation in self help community de...