The Impact of Feature Extraction and Selection on SMS Spam Filtering

Uysal, Alper Kürşat; Günal, Serkan; Ergin, Semih; Günal, Efnan Şora

doi:10.5755/j01.eee.19.5.1829

Cited by 42 publications

(37 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…WhatApps founded in the United State of America in 2010 and has been implemented in Malaysia. These applications function on each smartphone operating system [11]. The applications belong to young and adult generations under 9 until 60 years old for daily life.…”

Section: B Whatapps Messenger Applicationmentioning

confidence: 99%

A Generic Review of Messenger Application: Wechat And Whatsapp

Apon

Foozy

Shamala

2019

ijasce

View full text Add to dashboard Cite

Over the Internet today, communication environment is more easy and interesting to the citizen. There are much interesting in modern technology when they provided a good substrate for creating large-scale data sharing, content distribution, and application-level multicast applications. The important objective of this article is getting information about comparison of two distributed system in messenger application. Messenger application is known as a tool communication that can get any information. The distributed system is one of the independent and single coherent systems it was built an application that will be informed that section is being fixed or replaces to serve more applications or users. The distributed system for this article about the comparison of two distributed system in messenger application for WeChat and Whatsapp, it is also known as the famous application for this generations nowadays. Keywords Distributed System and Messenger ApplicationThe messenger application that is connected to the network can use separated by any distance of the user, maybe on separate continents or in the same building or same locations. In 15 modern technology, most of the messenger application is developed refer on-client server architecture [3]. For design application, in part of the client-server architecture, the interaction between multiple client and server are very important to the designer that needs to be considered because it taking account of the fact that every client interacts with others server at the same time [4]. In social media, the messaging application is tools that have deeply interpersonal communication with each other or grouping. It is social media tool that provides good real-time text transmission over the Internet. Software apps WeChat is the application in the category of social network timeline, quality branded account, games and a large popular to the mobile terminal is becoming major good business transaction platform. Besides that, WhatApps also have similar characteristics with WeChat for messaging application. WhatsApp also used for communication between the smartphones.

show abstract

Section: B Whatapps Messenger Applicationmentioning

confidence: 99%

A Generic Review of Messenger Application: Wechat And Whatsapp

Apon

Foozy

Shamala

2019

ijasce

View full text Add to dashboard Cite

show abstract

“…Some studies that are based on the SMS's contents were previously conducted by Joe and Shim [28], Hidalgo et al [21], Jie et al [29], Yadav et al [26], and Uysal et al [30]. But, Eshmawi and Nair [31] proposed feature based for SMS Spam detection based on the domain knowledge.…”

Section: Feature Selectionmentioning

confidence: 99%

A Comparative Study with RapidMiner and WEKA Tools over some Classification Techniques for SMS Spam

Foozy

Ahmad

Abdollah

et al. 2017

IOP Conf. Ser.: Mater. Sci. Eng.

View full text Add to dashboard Cite

Abstract. SMS Spamming is a serious attack that can manipulate the use of the SMS by spreading the advertisement in bulk. By sending the unwanted SMS that contain advertisement can make the users feeling disturb and this against the privacy of the mobile users. To overcome these issues, many studies have proposed to detect SMS Spam by using data mining tools. This paper will do a comparative study using five machine learning techniques such as Naïve Bayes, K-NN (K-Nearest Neighbour Algorithm), Decision Tree, Random Forest and Decision Stumps to observe the accuracy result between RapidMiner and WEKA for dataset SMS Spam UCI Machine Learning repository.

show abstract

“…The main drawback of the study is the computationalintensive processes at the client side of the mobile phone. Uysal et al (2013) investigated the impact of several features extraction and selection approaches on filtering SMS Spam messages in Turkish and English languages. The study combined the bag of words (BoW) model along with structural feature (SF) thus chi-square (CHI2) and Gini index (GI) metrics methods was used.…”

Section: Review Of Existing Sms Spam Filtering Approachesmentioning

confidence: 99%

“…Spam exists in other media as well, such as email, instant messages, search engines, Voice over Internet Protocol (VoIP), and newsgroup. Mobile networks have attracted large amounts of Spam due to the low cost of SMS messages and its increased usage (Uysal, Gunal, Ergin, & Sora Gunal, 2013;Yoon, Kim, & Huh, 2010). About 33.3% of SMS messages going around the world over mobile networks per seconds are Spam (Nuruzzaman, Lee, Abdullah, & Choi, 2012).…”

Section: Introductionmentioning

confidence: 99%

An Adaptive and Collaborative Server-Side SMS Spam Filtering Scheme Using Artificial Immune System

Onashoga

Abayomi‐Alli

Sodiya

et al. 2015

Information Security Journal: A Global Perspective

View full text Add to dashboard Cite

SMS Spam, which is an unsolicited or unwanted message, is a major problem with Global System for Mobile Communication (GSM) subscribers. Existing Spam filters have not been able to stop the SMS Spam problem due to frequent drift in spammer's words, limited bag of words for training, device portability, and high computational overhead of filters. This paper presents a collaborative and adaptive server-side SMS Spam filter using Artificial Immune System (coined ExAIS_SMS). The proposed scheme involves five modules: the innate mechanism, the user feedback, the quarantine, the tokenizer, and the immune engine. In this study, a new English corpus consisting of 5,240 SMS messages from 20 different users was collected for the study. A comprehensive experimental analysis on the SMS data set reveals the constant changes of Spam keywords and the impact of user feedback for system adaptability. In order to prove the efficiency of the proposed scheme, ExAIS_SMS was benchmarked with existing systems using the NUS corpus. The result gave an overall accuracy of 99% for ExAIS_SMS, 98% for Bayesian, and 97% for a client side AIS. The results showed that ExAIS_SMS is an efficient SMS Spam filtering technique, especially in resource constrained mobile phones.

show abstract

The Impact of Feature Extraction and Selection on SMS Spam Filtering

Cited by 42 publications

References 26 publications

A Generic Review of Messenger Application: Wechat And Whatsapp

A Generic Review of Messenger Application: Wechat And Whatsapp

A Comparative Study with RapidMiner and WEKA Tools over some Classification Techniques for SMS Spam

An Adaptive and Collaborative Server-Side SMS Spam Filtering Scheme Using Artificial Immune System

Contact Info

Product

Resources

About