LongSpam: Spam Email Detection using LSTM Algorithm
Nurhadi Wijaya, Yudianingsih, Evrita Lusiana Utari, Sugeng Winardi, Zaidir Zaidir, Agus Qomaruddin Munir · 2022 Seventh International Conference on Informatics and Computing (ICIC) · 2022
The email has swiftly become one of the most popular forms of communication because of its ease of use and speed on the internet. Not only is the email used for formal and informal correspondence, but it is also frequently utilized to transmit confidential information. Despite its widespread use, email has its drawbacks due to the persistent issues that its users continue to confront. Today's internet community faces serious challenges due to spam or unsolicited commercial communication. These flaws allow spammers to utilize email to spread their unwanted communications to tens of thousands of people. Here, we propose a detection model based on the LSTM algorithm for identifying spam and non-spam emails using a dataset from Kaggle comprising a total of 5.572 entries. The experimental findings show that the proposed model can successfully collect 1.115 samples as the test data and 4.457 samples as the training data. LongSpam has promise as a countermeasure against spam attacks since it can result in a lower threshold.