<![CDATA[The rapid development of digital communication technology has significantly increased the use of email, followed by the growing threat of spam emails that may disrupt user security and convenience. Spam emails are commonly used for advertisements, phishing attacks, and malware distribution, potentially causing financial losses and data theft. This study aims to implement a Deep Learning method based on Artificial Neural Network (ANN) to automatically detect spam emails and analyze the model performance using classification evaluation parameters. The research employed a quantitative experimental approach using a dataset of 10,000 emails consisting of spam and non-spam categories. The research stages included data preprocessing, text transformation using TF-IDF, ANN model training, system testing, and performance evaluation using accuracy, precision, recall, and F1-score metrics. The results showed that the ANN model achieved an accuracy of 96.4%, precision of 95.9%, recall of 96.7%, and F1-score of 96.3%. In addition, the pre-test and post-test results indicated a performance improvement of more than 11% after implementing the Deep Learning method. Based on these findings, the ANN method proved effective in improving the performance of spam email detection systems and can be utilized as a solution to support digital communication security more effectively.]]>
Copyrights © 2026
