A Machine Learning Based Email Spam Classification Framework Model: Related Challenges and Issues
Madan Lal1, Swati Agarwal2
1Deepika Mallampati*, Research Scholar, Osmania University, and Assistant Professor, Department of CSE, Neil Gogte Institute of Technology, Hyderabad, Telangana, India.
2Dr. Nagaratna P. Hegde, Professor, Department of CSE, Vasavi College of Engineering, Hyderabad, Telangana, India.
Manuscript received on January 12, 2020. | Revised Manuscript received on January 22, 2020. | Manuscript published on February 10, 2020. | PP: 3137-3144 | Volume-9 Issue-4, February 2020. | Retrieval Number: D1561029420/2020©BEIESP | DOI: 10.35940/ijitee.D1561.029420
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Spam emails, also known as non-self, are unsolicited commercial emails or fraudulent emails sent to a particular individual or company, or to a group of individuals. Machine learning algorithms in the area of spam filtering is commonly used. There has been a lot of effort to render spam filtering more efficient in classifying e-mails as either ham (valid messages) or spam (unwanted messages) through the ML classifiers. We may recognize the distinguishing features of the material of documents. Much important work has been carried out in the area of spam filtering which cannot be adapted to various conditions and problems which are limited to certain domains. Our analysis contrasts the positives methods as well as some shortcomings of current ML methods and open spam filters study challenges. We suggest some of the new ongoing approaches towards deep leaning as potential tactics that can tackle the challenge of spam emails efficiently.
Keywords: SVM, Machine learning, Deep Neural Network Neural Networks, Spam, Ham
Scope of the Article: Machine learning