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 3000
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
INFLUENCE OF IN-SERVICE TRAINING ON THE JOB PERFORMANCE OF LECTURERS IN COLLEGES OF EDUCATION IN NIGERIA
ABSTRACT
The study investigated the influence of in-service training on the job performance of lecturers in colleges of education in Nige...
ANALYSIS OF AGROFORESTRY PRACTICES IN KATSINA STATE, NIGERIA
ABSTRACT
The study investigated agroforestry farming among some international organizations, Nigerian Government, Kastina State Governmen...
GOVERNMENTAL ACCOUNTING FOR PUBLIC SECTOR ASSETS AND LIABILITIES
GOVERNMENTAL ACCOUNTING FOR PUBLIC SECTOR ASSETS AND LIABILITIES: This study aims to (i) evaluate the current practices in accounting for public se...
CHEMICAL AND BIOLOGICAL STUDIES OF HONEY BEE PROPOLIS COLLECTED FROM ZANGO KATAF LOCAL GOVERNMENT AREA OF KADUNA STATE, NIGERIA
ABSTRACT
Honeybee Propolis from Apis mellifera (Linn), has been used in ethno medicine as an emollient in the treatment of ringworm, meas...
TAX REVENUE AND INFRASTRUCTURAL DEVELOPMENT IN NIGERIA (1994–2017)
Background To The Study
Infrastructure is very significant to a country’s developmental prospect,...
THE INFLUENCE OF TEACHERS QUALIFICATION ON STUDENTS PERFORMANCE
Project Body
THE ROLE OF ORGANIZATIONAL CHANGE IN MOTIVATING EMPLOYEES
Abstract: THE ROLE OF ORGANIZATIONAL CHANGE IN MOTIVATING EMPLOYEES
Objective: This st...
THE IMPACT OF IFRS ADOPTION ON FINANCIAL REPORTING QUALITY
Abstract
This research investigates the impact of International Financial Reporting Standards (IFRS) ad...
EFFECT OF COVID-19 ON THE FINANCIAL PERFORMANCE OF SMEs IN NIGERIA
BACKGROUND OF THE STUDY
Nigeria is unquestionably one of Sub-Saharan Africa's major economies1. Whi...
ACTIVITIES OF SOME ANTIFUNGAL AGENTS AGAINST PHYTOPATHOGENIC YAM ROT FUNGI SPORES IN NIGERIA
ABSTRACT
Postharvest deterioration has been a major problem associated with yam storage for both farmers and traders and it is caused mos...
