Detecting SMS spam using a spam transformer model

Researchers in this study recommend a changed Transformer model to look at the conceivable outcomes of this model for SMS spam ID. As a feature of the UtkMl’s Twitter Spam Detection Competition dataset, our recommended spam Transformer is tried against laid out AI classifiers and cutting edge SMS sp...

Full description

Saved in:
Bibliographic Details
Main Authors: Mucha, Swetha, Gadipe, Sunitha, Poladi, Supraja, Shaik, Mohammed Ali, Yedulapuram, Sharvani
Format: Conference Proceeding
Language:English
Subjects:
Datasets
Transformers
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Researchers in this study recommend a changed Transformer model to look at the conceivable outcomes of this model for SMS spam ID. As a feature of the UtkMl’s Twitter Spam Detection Competition dataset, our recommended spam Transformer is tried against laid out AI classifiers and cutting edge SMS spam location draws near. ’ According to our tests on SMS spam distinguishing proof, the adjusted spam Transformer introduced here has the best exhibition of the multitude of applicants, with precision, review, and Fl-Score upsides of 98%, 0.945l, and 0.9613, separately. Additionally, the suggested model performs well on the UtkMl Twitter dataset, indicating that it may be applied to other issues of a similar kind.
ISSN:0094-243X
1551-7616
DOI:10.1063/5.0195868