SPAM DETECTION MODEL USING TENSORFLOW AND DEEP LEARNING ALGORITHM
DOI:
https://doi.org/10.37231/myjcam.2023.6.2.84Keywords:
Convolutional Neural Network , Recurrent Neural Network , Long Short-Term Memory, Spam EmailAbstract
As technology is becoming an integral aspect of every person's life since it makes living simpler and more efficient. As technology advances, spam attacks are becoming increasingly widespread. In this paper, we propose a solution to tackle this issue by comparing Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) deep learning techniques. Our objective is to develop a spam detection model that can effectively identify and filter out spam text. To evaluate the performance of our proposed model, we conducted experiments on a meticulously curated dataset consisting of spam and ham instances. The RNN model demonstrated exceptional accuracy, achieving an accuracy rate of 98.36%. Comparative analysis revealed that the CNN model achieved an accuracy rate of 97.10%, while the LSTM model attained an accuracy rate of 92.85%. These findings highlight the superior performance of the RNN model in accurately detecting spam using the TensorFlow platform. This research contributes to the advancement of spam detection methodologies, providing valuable insights for the development of effective spam filtering systems in the digital realm.
Downloads
Published
Issue
Section
License
Copyright (c) 2023 Malaysian Journal of Computing and Applied Mathematics
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors publishing with MyJCAM retain the copyright of their work under the Creative Commons Attribution License (CC-BY). This license allows others to copy, distribute, display, and perform the work, provided that the original work is properly cited.
By submitting a manuscript for publication, Authors agree to the following terms.
- Authors will own the copyright to the Article.
- The manuscript submitted for publication is the author’s original work.
- Authors hereby grant to MyJCAM a free and unrestricted license to disseminate the Article electronically to anybody who asks for it.
- All authors participated in the work in a substantive way and are prepared to take public responsibility for the work.
- All authors have seen and approved the manuscript as submitted.
- The manuscript has not been published and is not being submitted or considered for publication elsewhere.
- The text, illustrations and any other materials included in the manuscript do not infringe upon any existing copyright or other rights of anyone.
- No responsibility is assumed by MyJCAM, its staff or members of the editorial board for any injury or change to person or property as a matter of product liability, negligence or otherwise of any methods, product instruction or ideas contained in this publication.
