World Journal of Engineering Research and Technology

Prakash Mani Badal*

ABSTRACT

Messages have become an important component of our daily communication in today?s society, and the number of messages received by a user has increased significantly. There has been a large increase in the amount of spam messages in tandem with the rise in message volume. Spam communications are unsolicited mass messages that are sent to a large number of people. As a result, we get a lot of spam. These spam messages frequently obscure essential messages and may contain dangerous links that lead to harmful websites, jeopardising users? security. The bulk of spam classifiers are created using a single machine learning method, which may not be sufficient for correctly identifying a message as spam or ham. This thesis adds to the development of a Hybrid Spam classifier through the use of ensemble machine learning. In our research, a total of seven machine learning algorithms were shortlisted. These were then utilised to create 7 basic classifiers using a single method, 35 level 3 hybrid models using three algorithms, 21 level 5 hybrid models using five algorithms, and one level 7 hybrid model using seven algorithms. To narrow down the best hybrid models, a total of 64 models were trained and assessed.

[Full Text Article] [Download Certificate]