Popularity-Based Detection of Malicious
Content in Facebook Using Machine
Learning Approach
Somya Ranjan Sahoo and B. B. Gupta
Abstract In this world, people are encircled with various online social networks
(OSNs) or media platform, various websites and applications. This brings media
contents like texts, audio, and videos in daily basis. People share their current sta-
tus and moments with their belongings to keep in touch by using these tools and
software like Twitter, Facebook, and Instagram. The flow of information available
in these social networks attract the cybercriminals who misuse this information to
exploit vulnerabilities for their illicit benefits such as stealing personal information,
advertising some product, attract victims, and infecting user personal system. In
this paper, we proposed a popularity-based method which uses PSO-based feature
selections and machine learning classifiers to analyze the characteristics of different
features for spammer detection in Facebook. Our detection framework result shows
higher rate of detection as compared to other techniques.
Keywords Online social networks · PSO · Facebook · Machine learning
1 Introduction
In day-to-day life of human being, online social network or media become an inte-
gral part for sharing of knowledge, thoughts, and personal communication among
belongings and friends. Social networks like Facebook, Twitter, Instagram, and other
media-related networks are used by teenagers frequently in their work schedule. The
popularity of networks leads to get benefited by posting certain advertising, blogs,
and posts. Leading industries realize the usefulness of OSN sites for brand man-
agement and directly communicating with users for their benefits. Therefore, online
social networks are the origin of user’s personal information and commercial content
S. R. Sahoo · B. B. Gupta (B )
Department of Computer Engineering, National Institute of Technology, Kurukshetra,
Kurukshetra, Haryana, India
e-mail: gupta.brij@gmail.com
S. R. Sahoo
e-mail: somyaranjan.sahoo@gmail.com
© Springer Nature Singapore Pte Ltd. 2020
A. K. Luhach et al. (eds.), First International Conference on Sustainable Technologies
for Computational Intelligence, Advances in Intelligent Systems and Computing 1045,
https://doi.org/10.1007/978-981-15-0029-9_13
163