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
HERMENEUTICAL STUDY OF JONAH IN THE LIGHT OF JONAH- IT’S RELEVANCE TO COMTEMPORARY NIGERIA
Background of study
The book of Jonah is an Old Testament book composed of four chapters with forty-eight verses. The b...
A SURVEY ON DIROFILARIA IMMITIS AND ITS PREVALENCE IN DOGS IN ZARIA
EXCERPT FROM THE STUDY
Dirofilaria immitis: Is a common parasite of dogs (and some oth...
FACTORS RESPONSIBLE FOR THE DECLINING STANDARD OF SECONDARY EDUCATION IN MARU LOCAL GOVERNMENT AREA ZAMFARA STATE
ABSTRACT
The research study investigated and identified the factors responsible for the declining stand...
DISPATCH RIDER SYSTEM
ABSTRACT
This project (Design and Implementation of a Dispatch Rider System) is a logistics/delivery app that allows users to connect to...
THE EFFECT OF UNEMPLOYMENT ON ECONOMIC GROWTH IN NIGERIA (1980-2010)
ABSTRACT
The study was designed to investigate the effect of unemployment on economics growth in Nigeria for a period of 31 years (1980-2...
THE IMPACT OF MANAGEMENT COMMUNICATION FOR EFFECTIVE ORGANIZATIONAL PERFORMANCE
ABSTRACT
The focus of this study is “the impact of management communication for effective organizational performan...
PHARMACOGNOSTIC AND MOLECULAR STUDIES ON THE LEAF OF ALBIZIA CHEVALIERI (HARMS) (MIMOSOIDEAE)
ABSTRACT
Albiza chevalieri Harms (Mimosoideae) is a tree or shrub of 5-12 m tall and distributed in the dry savannah from Senegal, Niger...
THE IMPACT OF BUDGETING ON COST CONTROL
THE IMPACT OF BUDGETING ON COST CONTROL
This study aims to: (1) investigate the impact of budgeting on cost control, (2)...
AN INVESTIGATION INTO THE CHALLENGES OF POLLUTION AND AN ENGINEERING METHODS TO THE MANAGEMENT AND CONTROL OF INDUSTRIAL EFFLUENTS IN OTTA, NIGERIA
ABSTRACT
This study examined the effects of effluent discharges from various point-loads on a purposively selected recei...
PERCEPTION OF SUITORS ON PREMARITAL GENOTYPE SCREEINING INFORMATION IN ZARIA LOCAL GOVERNMENT AREA, KADUNA STATE, NIGERIA
Abstract
The study determined perception of suitors on premarital genotype screening information in Zaria local government area. Qualitat...
