FAKE PROFILE DETECTION USING MACHINE
LEARNING
TEAM MEMBERS
GUIDE NAME
1.KAVITHA L 210920205020 Mrs.D.ASHA (M.E)
2.MADHUMITHA S 210920205026
3.SELVI M 210920205040
ABSTRACT
Platforms for social media and others have a big impact on our lives. All across the world, people are
actively engaged in it.Fake accounts are regularly made by people, software, or machines. They are
employed in the spread of rumors and illegal actions like phishing and identity theft.This project uses
Machine learning to discriminate between fake and authentic Social media profiles based on the
dataset.The machine learning-based methods were used to perceive false accounts that could give the
wrong impression about people.The important traits are picked to judge the veracity of a social media
page.
Keywords
Social Media - World - Fake Profiles – Detection - Database
PROBLEM STATEMENT
How might we develop a Machine learning - based application to identify and
counter fake social media profiles? Tailored for investigative agencies and law
enforcement, enhancing profile authenticity and Security . To address the above
mentioned issue, we will develop a mobile application specialized in fake identity
detection equipped with predictive capabilities. The prediction will be generated by
selecting account-related features provided by the user .
OBJECTIVES
The main objective of this paper is to detect fake accounts.
Machine learning is used in this project to detect fake accounts accurately.
Identifying these fake accounts is that social media is flooded with false information, advertisements.
Utilize Machine learning to ensure the reliability of social media content, creating a more trustworthy
online environment.
Implement Machine learning technology to trace the origins of information, helping identify and verify
the source of content on social media platforms.
Enhance profile authenticity through advanced verification mechanisms. Implement robust security
measures to safeguard against fake profiles.
Provide a user-friendly interface for seamless interaction with the application . Collaborate with
stakeholders to gather insights and feedback for continuous improvement.
BLOCK DAIGRAM
EXISTING SYSTEM
• RANDOM FOREST ALGORITHM - Current systems don't consider enough factors when deciding
if an account is fake or real, which really affects how accurate they are. When they only look at a few
factors, they often make mistakes. Plus, people are getting better at making fake accounts, and the
software isn't keeping up. The main tool used to spot fake accounts is the Random Forest algorithm, but
it has its problems. It struggles with certain types of data and gets slower as you add more data to it.The
random forest algorithm to spot fake profiles can be tricky because it might get too good at learning
from the data, especially when there are way more fake profiles than real ones. When this happens, it
could focus too much on figuring out the majority (fake) profiles and not pay enough attention to the
real ones. So, even though it’s good at finding the most common type of profiles, it might miss out on
catching the fakes, which lowers its overall performance.Random forests can be quite demanding on the
computer, especially when there’s a lot of data or many different things to look at.
• ADVANTAGES :
* Automation of identifying and analysing the pattern.
* Scalability of analysing large volume of data in real time .
* Quickly process and classify the characteristics of provided information .
* ML models can continuously learn and adapt to new types of fake Profile and
Improving accuracy detection .
REFERENCE
[1] Chakra borty , Shazan.M M.Nahid , M., Ahmed, Md.K and
Talukder P.C. (2022) Fake Profile Detection Using Machine Learning Techniques. Journal of Computer
and Communications, 10, 74-87. https://doi.org/10.4236/jcc.2022.1010006
[2] Identification of Fake Accounts on Twitter Using Hybrid SVM Algorithm, Kodati, S., Reddy,
K.P.Mekala,S., Murthy, P.S., and Reddy, P.C.S.2021.Article No. 01046 of E3 S Web of Conferences, page
309.
https://doi.org/10.1051/e3sconf/202130901046
[3] Automated Fake Profile Detection Using Machine Learning on Instagram, Meshram, E.P.,
Bhambulkar, R. Pokale, P. Kharbikar, K. and Awachat , 2021. Journal of Scientific Research in
Science and Technology: International, 8, 117–127.
https://doi.org/10.32628/IJSRST218330
[4] Fake Social Media Profile Detection, Joshi, U.D.Singh, A.P., Pahuja, T.R., Naval, S., and Singal,
G.2021.Machine Learning Algorithms and Applications, edited by Srinivas, Sucharitha, G.Matta, and P.,
Scrivener Publishing LLC, Beverly, MA, pp. 193-209. https://doi.org/10.1002/9781119769262.ch11
• [5] K. Harish, R.Naveen Kumar, Dr. J. Briso Becky Bell March-April-2023 Volume 10, Issue 2
https://doi.org/10.32628/IJSRSET2310264
• [6]Using machine learning techniques, Faruque ,M.A., Rahman, S., Chakraborty, P., Choudhury, T.Uh,
J.S., and Singh, T.P. (2021) ascertain the polarity of the public's opinions on cricket in Bangladesh.30,
https://doi.org/10.1007/s41324-021-00403-8
• [7]Kodati, S., Reddy, K.P., Mekala, S., Murthy, P.S. and Reddy, P.C.S. (2021) Detection of Fake Profiles
on Twitter Using Hybrid SVM Algorithm. E3S Web of Conferences, 309, Article No. 01046.
https://doi.org/10.1051/e3sconf/202130901046
• [8]Meshram, E.P., Bhambulkar, R., Pokale, P., Kharbikar, K. and Awachat, A. (2021) Automatic
Detection of Fake Profile Using Machine Learning on Instagram. 8, 117-127
https://doi.org/10.32628/IJSRST218330
• [9] Muzammel, C.S., Chakraborty, P., Akram, M.N., Ahammad, K. and Mohibullah, M. (2022) Zero-
Shot Learning to Detect Object Instances from Unknown Image Sources. International Journal of
Innovative Technology and Exploring Engineering (IJITEE), 9, 988991.
https://doi.org/10.35940/ijitee.C8893.029420
• [10] Bharti, K. K., & Pandey, S. (2021). Fake account detection in twitter using logistic regression with
particle swarm optimization. Soft Computing, 25(16), 11333-11345.
https://doi.org/10.1109/ACCESS.2018.2796018
