LSTM Based Short Message Service (SMS) Modeling for Spam Classification

Raj, Hans; Yao, Wei; Banbhrani, Santosh Kumar; Dino, Soomro Pir

doi:10.1145/3231884.3231895

Cited by 22 publications

(12 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Result Kaytan and Hanbay [16] 95.05% Ubing et al [17] 92.5% Vrbančič, Fister, and Podgorelec [18] 94.4% Mohd Foozy [19] 95.53% This study 98.86% [20] 98.22% Kawade [21] 98.34% Raj et al [22] 96.17% Safie et al [23] 97.13% This study 99.46%…”

Section: Work Bymentioning

confidence: 96%

Fuzzy Modelling using Firefly Algorithm for Phishing Detection

Syahirah¹,

Arfian²,

Mezhuyev³

et al. 2019

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

A fuzzy system is a rule-based system that uses human experts' knowledge to make a particular decision, while fuzzy modeling refers to the identification process of the fuzzy parameters. To generate the fuzzy parameters automatically, an optimization method is needed. One of the suitable methods provides the Firefly Algorithm (FA). FA is a natureinspired algorithm that uses fireflies' behavior to interpret data. This study explains in detail how fuzzy modeling works by using FA for detecting phishing. Phishing is an unsettled security problem that occurs in the world of internet connected computers. In order to experiment with the proposed method for the security threats, a database of phishing websites and SMS from different sources were used. As a result, the average accuracy for the phishing websites dataset achieved 98.86%, while the average value for the SMS dataset is 97.49%. In conclusion, both datasets show the best result in terms of the accuracy value for fuzzy modeling by using FA.

show abstract

Section: Work Bymentioning

confidence: 96%

Fuzzy Modelling using Firefly Algorithm for Phishing Detection

Syahirah¹,

Arfian²,

Mezhuyev³

et al. 2019

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

show abstract

“…The proposed approach achieved accuracy of 98.33% for SV M algorithm with use of 10-fold Cross-Validation. Moreover, in (Raj et al, 2018), a Long Short-Term Memory (LSTM) based approach has been proposed, where Word2Vec tool has been used for converting simplified text into representation of words in a vector space. The experimental results depicted that the proposed approach has achieved accuracy with value equal to 97.5%.…”

Section: Related Workmentioning

confidence: 99%

SMS Spam Identification and Risk Assessment Evaluations

Mohasseb

Aziz

Kanavos

2020

Proceedings of the 16th International Conference on Web Information Systems and Technologies

View full text Add to dashboard Cite

Short Message Service (SMS) constitutes one of the most used communication medium. It has become an integral part of people's lives and like other communication media, SMS texts have been used for propagating spam messages. Despite the fact that a broad range of spam techniques have been proposed to reduce the frequency of such incidents, many difficulties are still present due to text ambiguity; there, the same words can be used in seemingly similar texts which makes it more difficult to identify spam messages. In this paper, we propose an approach for identifying and classifying spam SMS based on the Syntactical features and patterns of the message. The proposed approach consists of three main parts, namely Data Pre-processing, Features Extraction, and Classification. Experimental results show that the proposed approach achieves a good level of accuracy. In addition, to show the effectiveness of handling class imbalance on the classification performance, two additional experiments were conducted using the implementation of the SMOTE algorithm. There, the results depicted that handling class imbalance help in improving identification and classification accuracy. Furthermore, based on the above, a risk model has been proposed that addresses the risk probability and the impact of spam SMS.

show abstract

“…Aynı zamanda konuşma [22], metin işleme [23], müzik [24] ve sınıflandırma [25] uygulamalarında LSTM mimarileri kullanılmış ve başarılı sonuçlar alınmıştır.…”

Section: Long Short-term Memory (Lstm)unclassified

LSTM Deri̇n Si̇ni̇r Ağlari İle Üni̇versi̇te Gi̇ri̇ş Sinavindaki̇ Matemati̇k Soru Sayilarinin Konulara Göre Tahmi̇ni̇

Süzen¹

2019

NWSA

View full text Add to dashboard Cite

In this study, we proposed a model for estimating the number of questions in the long short term memory (LSTM) deep neural network (DNN) and the mathematics test in the university entrance exam. The data set of the model consists of 931 questions divided according to 16 subjects of the mathematics test for the years 1981-2018. The data set is divided into 80% for the training of the model and 20% for the test. Hypercritical parameters have been determined to provide high accuracy in time series estimation problems in the LSTM model. The number of questions for each subject group has been trained one by one in the time series model. As a result of the study, the average accuracy was 98.42% and the average accuracy was 96.82% in the test. The data set was compared with machine learning algorithms to measure the accuracy of the DNN algorithm used and LSTM DSA achieved the highest performance. As a result of study, the future studies will provide the development of robots to predict because of the high accuracy of the model.

show abstract

LSTM Based Short Message Service (SMS) Modeling for Spam Classification

Cited by 22 publications

References 5 publications

Fuzzy Modelling using Firefly Algorithm for Phishing Detection

Fuzzy Modelling using Firefly Algorithm for Phishing Detection

SMS Spam Identification and Risk Assessment Evaluations

LSTM Deri̇n Si̇ni̇r Ağlari İle Üni̇versi̇te Gi̇ri̇ş Sinavindaki̇ Matemati̇k Soru Sayilarinin Konulara Göre Tahmi̇ni̇

Contact Info

Product

Resources

About