Dynamic feature selection for spam detection in twitter

M. Salih Karakaşlı; Muhammed Ali Aydin; Serhan Yarkan; Ali Boyaci

doi:10.1007/978-981-13-0408-8_20

Dynamic feature selection for spam detection in twitter

M. Salih Karakaşlı, Muhammed Ali Aydin, Serhan Yarkan, Ali Boyaci

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

15 Scopus citations

Abstract

Social Networks continue to increase their popularity day by day. With the widespread availability of Internet access, interest of people in social networks has also increased significantly. The fact that, popularity of social media makes it tempting to use social media platforms for bad purposes. Malicious people are attempting to gain unfair profits by using fake accounts and various techniques. Among these initiatives, SPAM is one of the most frequently used methods. Today, SPAM attacks on social networks are increasing and many social network users are exposed to this and similar attacks. To identify SPAM users among billions of social network users, the examination of massive amounts of data requires a challenging large-scale data analysis. In this study, we group similar Twitter users and introduce a dynamic feature selection technique that use different features for each user groups instead of use static feature set and apply machine learning algorithms to classify spam users on Twitter.

Original language	English
Title of host publication	International Telecommunications Conference - Proceedings of the ITelCon 2017
Editors	Ali Boyaci, Ali Riza Ekti, Muhammed Ali Aydin, Serhan Yarkan
Publisher	Springer Verlag
Pages	239-250
Number of pages	12
ISBN (Print)	9789811304071
DOIs	https://doi.org/10.1007/978-981-13-0408-8_20
State	Published - 2019
Externally published	Yes
Event	1st International Telecommunications Conference, ITelCon 2017 - İstanbul, Turkey Duration: Dec 28 2017 → Dec 29 2017

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	504
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	1st International Telecommunications Conference, ITelCon 2017
Country/Territory	Turkey
City	İstanbul
Period	12/28/17 → 12/29/17

Funding

This work is also a part of the M.Sc. thesis titled Big Data Analysis in Social Media at Istanbul University, Department of Computer Engineering.

Keywords

Big data
Feature selection
Social media
Spam detection

Access to Document

10.1007/978-981-13-0408-8_20

Cite this

Karakaşlı, M. S., Aydin, M. A., Yarkan, S., & Boyaci, A. (2019). Dynamic feature selection for spam detection in twitter. In A. Boyaci, A. R. Ekti, M. A. Aydin, & S. Yarkan (Eds.), International Telecommunications Conference - Proceedings of the ITelCon 2017 (pp. 239-250). (Lecture Notes in Electrical Engineering; Vol. 504). Springer Verlag. https://doi.org/10.1007/978-981-13-0408-8_20

@inproceedings{74f746df2daa4247a26d7207e3d0c8e4,

title = "Dynamic feature selection for spam detection in twitter",

abstract = "Social Networks continue to increase their popularity day by day. With the widespread availability of Internet access, interest of people in social networks has also increased significantly. The fact that, popularity of social media makes it tempting to use social media platforms for bad purposes. Malicious people are attempting to gain unfair profits by using fake accounts and various techniques. Among these initiatives, SPAM is one of the most frequently used methods. Today, SPAM attacks on social networks are increasing and many social network users are exposed to this and similar attacks. To identify SPAM users among billions of social network users, the examination of massive amounts of data requires a challenging large-scale data analysis. In this study, we group similar Twitter users and introduce a dynamic feature selection technique that use different features for each user groups instead of use static feature set and apply machine learning algorithms to classify spam users on Twitter.",

keywords = "Big data, Feature selection, Social media, Spam detection",

author = "Karaka{\c s}lı, \{M. Salih\} and Aydin, \{Muhammed Ali\} and Serhan Yarkan and Ali Boyaci",

note = "Publisher Copyright: {\textcopyright} 2019, Springer Nature Singapore Pte Ltd.; 1st International Telecommunications Conference, ITelCon 2017 ; Conference date: 28-12-2017 Through 29-12-2017",

year = "2019",

doi = "10.1007/978-981-13-0408-8\_20",

language = "English",

isbn = "9789811304071",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Verlag",

pages = "239--250",

editor = "Ali Boyaci and Ekti, \{Ali Riza\} and Aydin, \{Muhammed Ali\} and Serhan Yarkan",

booktitle = "International Telecommunications Conference - Proceedings of the ITelCon 2017",

}

Karakaşlı, MS, Aydin, MA, Yarkan, S & Boyaci, A 2019, Dynamic feature selection for spam detection in twitter. in A Boyaci, AR Ekti, MA Aydin & S Yarkan (eds), International Telecommunications Conference - Proceedings of the ITelCon 2017. Lecture Notes in Electrical Engineering, vol. 504, Springer Verlag, pp. 239-250, 1st International Telecommunications Conference, ITelCon 2017, İstanbul, Turkey, 12/28/17. https://doi.org/10.1007/978-981-13-0408-8_20

Dynamic feature selection for spam detection in twitter. / Karakaşlı, M. Salih; Aydin, Muhammed Ali; Yarkan, Serhan et al.
International Telecommunications Conference - Proceedings of the ITelCon 2017. ed. / Ali Boyaci; Ali Riza Ekti; Muhammed Ali Aydin; Serhan Yarkan. Springer Verlag, 2019. p. 239-250 (Lecture Notes in Electrical Engineering; Vol. 504).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Dynamic feature selection for spam detection in twitter

AU - Karakaşlı, M. Salih

AU - Aydin, Muhammed Ali

AU - Yarkan, Serhan

AU - Boyaci, Ali

PY - 2019

Y1 - 2019

N2 - Social Networks continue to increase their popularity day by day. With the widespread availability of Internet access, interest of people in social networks has also increased significantly. The fact that, popularity of social media makes it tempting to use social media platforms for bad purposes. Malicious people are attempting to gain unfair profits by using fake accounts and various techniques. Among these initiatives, SPAM is one of the most frequently used methods. Today, SPAM attacks on social networks are increasing and many social network users are exposed to this and similar attacks. To identify SPAM users among billions of social network users, the examination of massive amounts of data requires a challenging large-scale data analysis. In this study, we group similar Twitter users and introduce a dynamic feature selection technique that use different features for each user groups instead of use static feature set and apply machine learning algorithms to classify spam users on Twitter.

AB - Social Networks continue to increase their popularity day by day. With the widespread availability of Internet access, interest of people in social networks has also increased significantly. The fact that, popularity of social media makes it tempting to use social media platforms for bad purposes. Malicious people are attempting to gain unfair profits by using fake accounts and various techniques. Among these initiatives, SPAM is one of the most frequently used methods. Today, SPAM attacks on social networks are increasing and many social network users are exposed to this and similar attacks. To identify SPAM users among billions of social network users, the examination of massive amounts of data requires a challenging large-scale data analysis. In this study, we group similar Twitter users and introduce a dynamic feature selection technique that use different features for each user groups instead of use static feature set and apply machine learning algorithms to classify spam users on Twitter.

KW - Big data

KW - Feature selection

KW - Social media

KW - Spam detection

UR - https://www.scopus.com/pages/publications/85049965364

U2 - 10.1007/978-981-13-0408-8_20

DO - 10.1007/978-981-13-0408-8_20

M3 - Conference contribution

AN - SCOPUS:85049965364

SN - 9789811304071

T3 - Lecture Notes in Electrical Engineering

SP - 239

EP - 250

BT - International Telecommunications Conference - Proceedings of the ITelCon 2017

A2 - Boyaci, Ali

A2 - Ekti, Ali Riza

A2 - Aydin, Muhammed Ali

A2 - Yarkan, Serhan

PB - Springer Verlag

T2 - 1st International Telecommunications Conference, ITelCon 2017

Y2 - 28 December 2017 through 29 December 2017

ER -

Dynamic feature selection for spam detection in twitter

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this