|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
It is common practice for humans, bots, and other automated systems to create new user accounts using stolen or otherwise fraudulent personal data. They are used in deceptive practices like as phishing and identity theft as well as in the propagation of malicious rumors. A single malicious actor may create hundreds or even thousands of fake accounts in order to spread their malicious activities to as many real users as feasible. Users may learn a great lot from social networking platforms. Hackers have an open invitation to exploit this trove of social media data. These cybercriminals create false personas and spread pointless content. There is a critical step in navigating social media networks that involves identifying fake profiles. In this research, we offer a machine learning method for spotting Instagram phoney profiles. We used the attribute-selection technique, adaptive particle swarm optimization, and feature-elimination recursion in this strategy. The findings show that the proposed adaptive particle swarm optimization approach outperforms RFE in terms of accuracy, recall, and F measure.
Keyword
Fake account, Machine Learning, Feature Selection, Adaptive Particle Swarm Optimization, Recursive Feature Elimination
PDF Download (click here)
|
|
|
|
|