CYBERBULLYING DETECTION USING WEAKLY SUPERVISED AND FULLY SUPERVISED LEARNING
- Project Research
- 1-5 Chapters
- Abstract : Available
- Table of Content: Available
- Reference Style: APA
- Recommended for : Student Researchers
- NGN 5000
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.
Related Project Materials
An assessment of the socio-economic effects of traditional mortuary rites in Uhunmwonde Local Government, Edo State
Background of the Study:
Traditional mortuary rites in Uhunmwonde Local Government are deeply embedded in cultural practice...
The Effect of Delayed Payment of Salaries on Staff Performance in Public Universities in Sokoto State
Background of the Study
Delayed payment of salaries in public institutions is a signif...
A Comparative Study of E-Commerce Strategies and Their Impact on Business Performance: A Study of Online Retailers in Niger State
Background of the Study
E-commerce has revolutionized the retail industry, providing b...
THE EFFECT OF INADEQUATE HUMAN RESOURCE ON THE PERFORMANCE OF GOVERNMENT ESTABLISHMENTS
ABSTRACT
This study was carried out to examine the the effect of inadequate human resource on the perfo...
The Impact of Customer Service Training on Staff Performance in Banking: A Case Study of Sterling Bank
Background of the Study
Customer service training is essential for enhancing the performance of banking staff and improving the overall c...
An Investigation of the Impact of Infrastructure Modernization on Regional Economic Disparities in Nigeria
Background of the Study
Infrastructure modernization involves upgrading and expanding the physical and te...
The Relationship Between Corporate Governance and Real Estate Investment Trust (REIT) Performance in Abuja
Background of the Study
Corporate governance refers to the structures and processes through which organizations are directed and controll...
A SURVEY OF THE PROBLEMS OF COMPUTERIZATION OF OFFICE FUNCTIONS IN SELECTED BUSINESS ESTABLISHMENT IN AGUATE L.G.A
ABSTRACT
The contribution of the Business Establishment to the economic development of any nation cannot be over emphasi...
An Appraisal of the Effects of GDP and Inflation on Fiscal Policy Adjustments in Nigeria
Background of the Study:
Fiscal policy in Nigeria is shaped by various macroeconomic factors, notably GDP growth and inflat...
A Critical Analysis of Financial Planning and Wealth Management Strategies in Niger State
Background of the Study
Financial planning and wealth management are critical for both individuals and businesses to ach...
