Research Article
Analysis of e-Mail Spam Detection Using a Novel Machine Learning-Based Hybrid Bagging Technique
| | Assessment parameter | Specification | Model |
| | Precision | The efficacy of the classifier is defined by precision | | | Accuracy | The proportion of positive forecasted value to the overall set | | | Recall | The positively labeled information provided by the classification out of the entire data | | | F-score | Overall quality is demonstrated by the classifier’s ability to produce efficient beneficial results. | | | True-negative rate () | Spam mails managed to identify as a percentage of all spam mails. | | | False-negative rate () | It detects the number of spam e-mails that have been missed. | | | False-positive rate () | The number of spam e-mails mistakenly detected as a proportion of overall spam mails | | | True positive () | The sum of ham electronic mails that were accurately detected. | — | | False negative () | The sum of ham mails that have been mistakenly classified as spam. | — | | False positive () | The sum of spam messages that were mistakenly recognized as ham. | | | True negative () | The sum of spam e-mails that were appropriately detected.- | — |
|
|
