Application of Large Language Models for Spam Detection

Merida Ramos, Jose Fernando (2024) Application of Large Language Models for Spam Detection. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (926kB) | Preview
Preview	PDF (Configuration Manual) Download (720kB) | Preview

Abstract

Spam messages in emails and SMS are a raising problem, often containing scams, malware, or unwanted ads. Detecting spam is essential to protect users and improve communication. This project combines BERT (Bidirectional Encoder Representations from Transformers) and SVM to enhance SMS spam detection. BERT processes messages to capture their meaning, while SVM classifies them as spam or ham.

By using the SMS Spam Collection dataset, the study compares the BERT-SVM model with Traditional Text Classification. The results demonstrate that BERT-SVM outperforms older techniques in precision, recall, and accuracy. An API was also built to test the model’s real-world performance. This project emphasizes the potential of large language models in spam detection and recommends exploring lighter versions of BERT for future use.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Prior, Michael UNSPECIFIED
Uncontrolled Keywords:	Spam; BERT; SVM; Large Language Models; Spam detection
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Ciara O'Brien
Date Deposited:	23 Jul 2025 15:18
Last Modified:	23 Jul 2025 15:18
URI:	https://norma.ncirl.ie/id/eprint/8226

Actions (login required)

View Item