Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal Jurnal Infra
Hendy Gunawan
Program Studi Teknik Informatika, Universitas Kristen Petra Surabaya
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Penerapan Machine Learning dalam mendeteksi Fake Account pada Instagram Hendy Gunawan; Yulia Yulia; Gregorius Satia Budhi
Jurnal Infra Vol 10, No 2 (2022)
Publisher : Universitas Kristen Petra

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Instagram is the fourth most used social media in terms of the number of active users. Currently, many people are trying to increase the number of followers for other reasons such as gaining fame or wanting to be famous and trustworthy by people because they have a large number of followers. Therefore, people create fake accounts that are used to increase the number of their followers and also as a place to commit crimes such as fraud and cyberbullying. Such flexibility and spread of use has made Instagram a platform used for the proliferation of fake accounts. In this research, a website based application was designed that can detect accounts on Instagram whether they are fake or real accounts. The detection is carried out using machine learning with the Support Vector Machine, Naïve Bayes, Random Forest and Adaptive Boosting methods to detect fake or real accounts on Instagram. The method used is compared to its performance to find which method is the most appropriate in detecting fake or real accounts on Instagram. The use of k-fold cross validation is used to prevent overfitting in machine learning. Based on the tests that have been carried out, that AdaBoost can be used for account classification on Instagram with an accuracy of 92.5%, Random Forest 91.7%, Support Vector Machine 90.7% and Naïve Bayes 83.6%.
Co-Authors Gregorius Satia Budhi Yulia Yulia