Monitoring Suspicious Discussions on Online Forum Using Deep Learning Techniques
| dc.contributor.author | Oluranti John AFOLABI | |
| dc.date.accessioned | 2024-05-23T12:26:13Z | |
| dc.date.available | 2024-05-23T12:26:13Z | |
| dc.date.issued | 2022-12 | |
| dc.description.abstract | Nowadays, people are passionate about using the internet in their daily lives. This is rapidly increasing the use of online forums. An online forum is nothing but a medium to share one's thoughts, feelings and emotions towards specific pictures, videos and paintings etc. This leads to the execution of many legal and illegal activities. These illegal activities are trading black money online, distributing copyrighted movies and using illegal words. Law enforcement needs a system to effectively deal with this problem. Network Intrusion Detection System (NIDS) help system administrators detect network security vulnerabilities in their organization. However, many challenges arise when developing a flexible and effective NIDS for unplanned and unpredictable attacks. In this thesis, we propose a deep learning-based approach to develop a flexible and efficient NIDS to analyse suspicious and criminal activities occurring in forums. Deep learning technique is used, Natural Language Processing (NLP) for suspicious keyword extraction and Support Vector Machine (SVM) for detection and classification of suspicious keywords. We present the performance of our approach and compare it with some previous works. The metrics to be compared include accuracy, precision, recall, and f-measure values. Keywords: online forum; machine learning; deep learning; natural language processing; support vector machine. Word Count: 187 | |
| dc.identifier.citation | Kate Turabian | |
| dc.identifier.other | M.Sc | |
| dc.identifier.uri | https://repository.lcu.edu.ng/handle/123456789/335 | |
| dc.language.iso | en | |
| dc.publisher | Lead City University | |
| dc.relation.ispartofseries | M.Sc | |
| dc.title | Monitoring Suspicious Discussions on Online Forum Using Deep Learning Techniques | |
| dc.type | Thesis |