Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2025
|
| Online Access: | https://doi.org/10.5281/zenodo.15612471 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- <p>It is difficult to identify SMS spam when categorising texts and using Naive Bayes has been effective. The aim of this approach is to sort messages you receive into spam and ham. The system uses the presence of words in a message to determine if it most likely belongs to a specific class. We present an improved and fast approach to SMS spam detection using the Naive Bayes method. Initially, the approach uses tokenization, removes stop words and performs stemming to choose the important features. After that, Naive Bayes uses a labelled set of messages to identify the chances of occurrence of each word in spam or ham categories. The model is then used to cheque if new messages are spam or ham. The results from experiments support that the method achieves a high rate of correct detection for SMS spam</p>