| Autor: |
Kumar, Kummuneni Naveen, Kumari, V. Sheeja, Ramesh, S. |
| Předmět: |
|
| Zdroj: |
AIP Conference Proceedings; 2024, Vol. 3168 Issue 1, p1-5, 5p |
| Abstrakt: |
The primary objective of this research is to demonstrate that the K Nearest Neighbor method is superior to the Naive Bayes method when it comes to identifying anonymous spammers. Both the materials and the methods are as follows: This article's implementation uses two groups: group 1 as K Nearest Neighbor, and group 2 as Naive Bayes. Both of these groups are described below. There are twenty people in each of the groups that make up the sample, and the size of the sample was estimated by utilizing the Clincalc software with a GPower pretest of 80%, threshold of 0.05, and confidence interval of 95%. Results show that the accuracy rate of the K Nearest Neighbor algorithm is 93%, while the accuracy rate of the Naive Bayes algorithm is 89%; hence, the KNN algorithm has a better accuracy rate than the NB algorithm. An independent significant value of 0.001 was found using SPSS, and the probability level was found to be 0.05. This demonstrates that there is a difference between the two approaches that were taken into consideration in this study that is statistically significant. When contrasted with Naive Bayes, the K Nearest Neighbor algorithm yields findings with a higher accuracy rate, making it more suitable for the efficient reconnaissance of anonymous spam. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
