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
AUDITING AS AN AID TO ACCOUNTABILITY IN THE PUBLIC SECTORS (A CASE STUDY OF FEDERAL MINISTRY OF FINANCE AND ECONOMIC DEVELOPMENT)
Background Of The Study
This is now a national issue. The increasing incidence of fraud and misappropri...
PRAGMATIC ANALYSIS OF WHATSAPP CHATS
Abstract
WhatsApp has significantly penetrated the various spheres of peoples’ lives all over the...
EFFECTIVE TRAINING AS A TOOL FOR IMPROVING BUILDING SERVICES IN ENGINEERING PRACTICE
ABSTRACT
It has being observed over time that there are problems associated with the quality of designs and execution of jobs within the...
INFLUENCE OF OPINION LEADERS IN THE DEVELOPMENT
Background of the study
In the post-second World War years, development co-operation was based on transfer of technologies to developing...
PROJECT FINANCING: CHALLENGES AND THE WAY FORWARD.
ABSTRACT
Project transport represents a dominant force in the transport industry in developing countries. It therefore s...
EFFECT OF INNOVATION TOWARDS MEETING CUSTOMER SATISFACTION IN NIGERIA BANKING SECTOR
ABSTRACT
This research examined the effect of motivation in meeting customer’s satisfaction in the banking sector....
EVALUATION OF THE USE OF MANGOPEEL, BANANAPEEL AND ALLIGATOR PEPPER PODEXTRACTASCORROSION INHIBITOR ON CARBON STEELINACIDICMEDIUM.
ABSTRACT
This work investigates the use of extract of alligator pepper pod, mango peel and banana peel asinhibitors to carbon steel corro...
HOME ENVIRONMENT AND ITS EFFECT ON ACADEMIC PERFORMANCE AMONG SECONDARY SCHOOL STUDENTS
ABSTRACT
The home influences the students at the most possible time of his life at a time when his mind...
SOCIAL MEDIA ADVERTISING AND ITS INFLUENCE ON AUDIENCE PREFERENCE OF SIMILAR PRODUCT
ABSTRACT
This study was carried out to examine social media advertising and its influence on audience preference of simi...
THE IMPACT OF CBN CASHLESS POLICY ON THE DEVELOPMENT OF THE BANKING SECTOR OF NIGERIA
STATEMENT OF THE PROBLEM
As more payment systems have been introduced, pundits have been predicting the emergence of a &...
