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
THE ADVENT OF MODERN COMMUNICATION GADGETS: IMPLICATIONS FOR NIGERIAN JOURNALISM
ABSTRACT
The advent of modern communication gadget –implication for Nigerian Journalism. The tittle of this study took a vivi...
STEALING AMONG STUDENTS: CAUSES AND REMEDIES
Abstract
This study was carried out on stealing among students. This study reports students, teachers, deputy principal...
ASSESSMENT OF ENTREPRENEURSHIP EDUCATION ON SELF-EMPLOYABILITY AMONG BUSINESS EDUCATION GRADUATES
Background of the Study
Business education is a course that prepares for entry into an advancement in jobs within busin...
EXAMINATION ON THE CHALLENGES AND QUALITIES OF A GOOD TEACHER
ABSTRACT
This study was carried out to examine the challenges and qualities of a good teacher using 6 s...
EVALUATION OF THE IMPACT OF INTERNAL AUDITING ON THE PERFORMANCE OF INSURANCE FIRMS IN NIGERIA
Background of the Study
Globally, auditing is an independent review of an economic entity that is estab...
PRIMARY EDUCATION IN NIGERIA-CHALLENGERS AND PROSPECTS
ABSTRACT
The research topic is “challenges and prospects of Primary education” in Nnewi Sou...
EXAMINING THE INFLUENCE OF EARLY CHILDHOOD EDUCATION ON SOCIAL SKILLS IN RURAL COMMUNITIES
ABSTRACT: Examining the influence of early childhood education on so...
CLUSTERING NEWS ARTICLES USING K-MEANS AND N-GRAMS
ABSTRACT
Document clustering is an automatic unsupervised machine learning technique that aimed at grouping related set of items into clu...
THE IMPACT OF FOREIGN EXCHANGE MANAGEMENT ON THE NIGERIAN ECONOMY
ABSTRACT
This research work investigates the impact of foreign exchange management by the monetary auth...
EXPLORING THE IMPACT OF NANOTECHNOLOGY EDUCATION IN VOCATIONAL TRAINING
ABSTRACT: Exploring the impact of nanotechnology education in vocational training is pivotal to understanding how emerging technologies shape...
