Open AccessSpam Mail Detection Using Optimization Techniques
Author(s) -
Koneru Anupriya,
Kurakula Harini,
Kethe Balaji,
Karnati Geetha Sudha
Publication year - 2022
Publication title -
ingénierie des systèmes d'information/ingénierie des systèmes d'information
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.161
H-Index - 8
eISSN - 2116-7125
pISSN - 1633-1311
DOI - 10.18280/isi.270119
Subject(s) - computer science , naive bayes classifier , decision tree , random forest , machine learning , spamming , precision and recall , python (programming language) , support vector machine , artificial intelligence , the internet , data mining , classifier (uml) , world wide web , operating system
On account of the widespread availability of internet access, email correspondence is one among the most well-known cost-effective and convenient method for users in the office and in business. Many people abuse this convenient mode of communication by spamming others with conciseness bulk emails. They use emails to collect personal information of the users to benefit financially. A literature review is conducted to investigate the most effective strategies for achieving successful outcomes while working with various spam mail datasets. K-Nearest Neighbor, Support Vector Machine, Naive Bayes, Decision Tree, Random Forest, and Logistic Regression are all employed in the implementation of machine learning techniques. To make classifiers more efficient, bio-inspired algorithms such as BAT and PSO are used. The accuracy of every classification algorithm along with and without optimization is observed. Factors such as accuracy, f1-score, precision, and recall are used to compare the results. This work is implemented in Python along with GUI interface Tkinter.