A Systematic Literature Review on SMS Spam Detection Techniques

Lota, Lutfun Nahar; Hossain, Belal

doi:10.5815/ijitcs.2017.07.05

Cited by 11 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Several articles reviewed the previous and current approaches for SMS spam according to various metrics [1][2][3][4][5][6][7]. The most detailed and valuable review was presented in [1], it covers most of the SMS applications, approaches and methods.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

The Impact of Deep Learning Techniques on SMS Spam Filtering

Gomaa¹

2020

IJACSA

View full text Add to dashboard Cite

Over the past decade, phone calls and bulk SMS have been fashionable. Although many advertisers assume that SMS has died, it is still alive. It is one of the simplest and most cost-effective marketing tools for companies to communicate on a personal level to their customers. The spread of SMS has led to the risk of spam. Most of the previous studies that attempted to detect spam were based on manually extracted features using classical machine learning classifiers. This paper explores the impact of applying various deep learning techniques on SMS spam filtering; by comparing the results of seven different deep neural network architectures and six classifiers for classical machine learning. Proposed methodologies are based on the automatic extraction of the required features. On a benchmark data set consisting of 5574 records, a fabulous accuracy of 99.26% has been resulted using Random Multimodel Deep Learning (RMDL) architecture.

show abstract

Section: Related Workmentioning

confidence: 99%

“…They also concentrated on the weaknesses of existing studies and pointed out the paths for future research. Authors in [3] considered 17 papers and reviewed their algorithms, approaches, used databases, benefits, drawbacks, and methods of evaluation. In addition, they explained the classical machine learning classification problems.…”

Section: Related Workmentioning

confidence: 99%

The Impact of Deep Learning Techniques on SMS Spam Filtering

Gomaa¹

2020

IJACSA

View full text Add to dashboard Cite

show abstract

“…Our Assessment was carried out with the intention of reviewing all the methods and procedures applied in SMS spam identification. Numerous datasets were evaluated using various models to test the spam of SMS messages in various research publications, and it was determined which model provided the highest level of accuracy [10]. SVM, naive Bayes, decision trees, and k nearest neighbours are the models that have been employed most frequently in studies.…”

Section: Comparison With Existing Solutionsmentioning

confidence: 99%

Spam SMS Classifier using Machine Learning Algorithms

et al. 2024

IJFMR

View full text Add to dashboard Cite

Mobile SMS communication is insecure as a result of a significant problem with spam detection. A technique or model with high accuracy and precision is required to address this spam SMS issue. The amount of spam emails has dramatically increased over the last few years. SMS spam has major negative impacts since it harms both consumers and service providers, eroding their mutual trust to a great extent. Different types of classifier algorithm have been implemented like Naïve bayes, Random Forest, KNN and Support vector classifier on a raw dataset collected from UCI repository in this research. Metrices like Accuracy, Precision and Recall are takes as performance metrics for calculating the efficiency of the algorithm. After experimenting, the result of these algorithms and compared them with another models. We showed the comparison using Visualization Techniques.

show abstract

“…No estudo de [27] os autores conduziram uma revisão sistemática de literatura (2006-2016) para identificar técnicas de deteção de spam de SMS. A triagem realizada em 11 bibliotecas de artigos científicos permitiu identificar 17 estudos relevantes para a pesquisa.…”

Section: Trabalhos Relacionadosunclassified

Prediction of bank frauds by SMS or voice, from cell phone data analysis: A Systematic Literature Review

Cossa

Sousa

Martins

et al. 2021

2021 16th Iberian Conference on Information Systems and Technologies (CISTI)

View full text Add to dashboard Cite

Resumo-Nos últimos anos registou-se um crescimento acentuado de fraudes bancárias cometidas por SMS (Short Messaging System) e voz. Um dos fatores que contribui para o aumento de casos de fraudes por SMS é o baixo custo de aquisição de grandes volumes de mensagens, a confiabilidade (a mensagem chegará ao destinatário) e o fato de não precisar de Internet para chegar até a vítima. Em relação as fraudes financeiras por voz, estas podem ser usadas para persuadir as vítimas a efetuarem transferências bancárias para as contas dos fraudulentos, com a promessa de receber avultadas somas em prémios. A deteção destes tipos de fraudes não é uma tarefa trivial, pois exige a aplicação de técnicas e métodos apropriados dependendo da sua natureza. Assim, neste artigo é apresentada uma Revisão Sistemática de Literatura (RSL) de 2015 a 2020, com o intuito de analisar o estado da arte sobre fraudes bancárias cometidas por SMS ou voz. A RSL permitiu identificar os tipos mais comuns de fraudes bancárias por SMS ou voz, e as respetivas técnicas de deteção. Palavras Chave -Fraudes financeiras por SMS; fraudes no dinheiro móvel; Análise de CDR.

show abstract

A Systematic Literature Review on SMS Spam Detection Techniques

Cited by 11 publications

References 17 publications

The Impact of Deep Learning Techniques on SMS Spam Filtering

The Impact of Deep Learning Techniques on SMS Spam Filtering

Spam SMS Classifier using Machine Learning Algorithms

Prediction of bank frauds by SMS or voice, from cell phone data analysis: A Systematic Literature Review

Contact Info

Product

Resources

About