Spam Text Detection Using Machine Learning Model

This research presents a classification between spam and non-spam messages by removing duplicate sentences or words; meaningless words and various marks. The data is then classified by machine learning techniques and compared by differences between the datasets. Quantitative transformations were performed on each model to find the most efficient model which can filter spam messages efficiently and quickly. By getting the best comparison results in terms of information, quantitative conversation and model are used. The experimental results showed that, of all the tests, the model that performed best was Random Forest, with an average accuracy of 97.