International Journal of Innovative Research in Computer Science & Technology (IJIRCST)
ISSN (online): 2347-5552, Volume-11, Issue-2, March 2023
https://doi.org/10.55524/ijircst.2023.11.2.9
Article ID IRP1374, Pages 44-49
www.ijircst.org
Innovative Research Publication 44
A Review Article on Detection of Fake Profile on Social-Media
Shamim Ahmad
1
, and Dr. Manish MadhavaTripathi
2
1
M.Tech. Scholar, Department of Computer Science and Engineering, Integral University, Lucknow, India
2
Associate Professor, Department of Computer Science and Engineering, Integral University Lucknow, India
Copyright © 2023 Made Shamim Ahmad et al. This is an open access article distributed under the Creative Commons Attribution License,
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
ABSTRACT- Nowadays, practically everyone, from a
youngster to an adult, spends more time on online social
media platforms, connecting with and exchanging
information with individuals all over the world. The social
network is becoming a popular means to communicate
with people who live in different parts of the world.
Because of the tremendous interconnectedness and
information sharing enabled by the internet, social media
platforms. This highlights the importance of establishing a
system capable of detecting fake profiles on social media
networks. There has been a lot of study done in this area
utilising machine learning algorithms to identify fake
profile, duplicate, spam, and bot accounts, and most of the
fake profile accounts were effectively recognised using
machine learning algorithms. This study discusses fake
profile detection on social networks using machine
learning.
KEYWORDS- Fake Profile, Fake Identities, Security
Issues, Social Network Analysis, Machine Learning
I. INTRODUCTION
Every user of a social networking site has a profile and can
communicate with friends, exchange updates, and network
with new people. These social networks leverage Web 2.0
technology, which facilitates user communication. These
social networking sites expand swiftly and alter how
people connect with one another. Via the online
community, people with similar interests can meet and
form connections. social effect During your contemporary
generation, online social connections have become integral
to everyone's social life. Most people are connected to
some of these websites. OSNs like Instagram, Facebook,
Google+, Twitter, LinkedIn, and Pinterest, among others,
are expanding as a result of their free memberships and
cost-free information sharing with other users. and they
have become an essential part of life in today’s generation.
There are several disadvantages to the expanding use of
OSNs, including a higher likelihood of fraudulent profiles,
identity theft, privacy breaches, etc. False profile
development has increased in tandem with the growth in
social network users. This has contributed to a rise in
cybercrime over the past few years.
Hackers exploit these sites to disseminate rumours, hate
speech, and false information and to earn money
unlawfully by setting up several bogus profiles. Also,
people are making fictitious profiles to further their own
interests, such as obtaining referral bonuses or an increase
in votes in online voting systems. Researchers use social
bots, which are automated programmes, to carry out their
tasks. The fake accounts exist anywhere on the internet,
such as on social networks, online dating websites,
discussion blogs, shopping websites, etc. As social media
platforms are used more often, users and platform
providers are becoming increasingly concerned about the
issue of fraudulent profiles. To propagate false
information, con individuals, or carry out other nefarious
deeds, fake profiles might be made. By examining a variety
of profile data and user behaviour, machine learning
techniques can be utilised to identify these fraudulent
profiles.
Figure 1: Analysing Model of Real Fake Detection
The detection of fake profiles using machine learning
involves building a model that can classify a given profile
as either genuine or fake. The model can be trained using
a dataset of known fake and genuine profiles. The dataset
can be collected using various methods, such as manual
identification by experts, crawling social media platforms,
or using crowd sourcing.
The features of the profiles that can be used for
classification include the profile picture, name, location,
age, gender, profile description, number of followers,
friends, and posts, engagement rate, activity time, and
content. Machine learning algorithms, such as decision
trees, random forests, support vector machines, and neural
networks, can be used to extract features from the profiles
and classify them as genuine or fake.
Once the model is trained, it can be used to classify new
profiles automatically. However, the performance of the
model depends on the quality of the dataset, the choice of
features, and the algorithm used. The model may also need
to be updated periodically to adapt to new techniques used
by fake profile creators.